tierlist.tech
中EN

08.24 Today's Picks

357 new projects found today, 291 rated.

Created 2026-08-22 – 2026-08-24Fetched 300Filtered 50

S · Look today

S

sentio

truesparRust

It addresses AI agents' lack of a dedicated mailbox by providing a complete email send/receive API. Rust performance and email protocol support have earned it quick attention in the AI tool ecosystem; it could commercialize as a hosted service or become a standard dependency, with the risk being existing email APIs like Resend and complex operations.

Email inbox API for AI agents. Give every agent its own real email address, receive mail as structured webhooks, and reply in-thread over REST. A complete multi-tenant mail server in Rust: inbound and…

#AI Agents#Email#APIs

★35

A · Worth watching

A

watermark-remover

ShadowAqueductPython

Addresses multi-vendor AI watermark removal for content detection and tracing; 760 stars in two days show strong emotional demand, but it involves evading AI detection and copyright risk. Commercialization is a content-cleaning API, but ethical and legal risks are extremely high, similar tools compete, and platform countermeasures may appear quickly.

Purge multi-vendor AI watermarks: clean Unicode text, apply statistical rewrite hooks, and clear C2PA plus metadata from PNG, JPEG, SVG, PDF, DOCX, HTML, and MD.

#Watermarks#Images#Documents

★760

A

slotstream

halarewichRust

The platform provides real-time observability for the Solana blockchain, solving developers' pain of monitoring block and transaction performance. As a Rust cross-language solution, its 39 stars in two days show early attention. Monetization could position it as a standard Solana ecosystem monitoring tool or SaaS. The biggest risk is existing competitors like QuickNode and the project's early stage lacking stability validation.

Polyglot real-time observability platform for the Solana blockchain

#Observability#Monitoring#Blockchain#solana

★39

A

Wbrowser

w-partnersJavaScript

Drives your already-logged-in Chrome via CDP, taking commands from a terminal or any AI assistant, MCP-ready. It hits the pain point of agents needing to reuse real browser sessions, more practical than spinning up a fresh headless browser each time; the obvious issue is that handing login state to agent calls requires clear permission boundaries.

Drive the Chrome you are already logged into - from your terminal or any AI assistant. Cross-platform, MCP-ready.

#MCP#AI Agents#CLI#Automation#chrome

★22

A

ReclaimArc

harlixay7Rust

In-place extraction on Windows that reclaims archive space as it unpacks, so a 100GB package can be extracted on a 10GB free disk. The problem is specific and the approach rare, but with few stars and immature code, validate reliability on small data first.

Transactional in-place archive extractor for Windows that progressively reclaims disk space from archives as it extracts. Extract 100 GB files with only 5-10 GB of free space.

#Windows#CLI#Performance

★6

A

ecobee-local

addition-officialPython

Bypasses the Ecobee cloud and official API key by pairing locally via HomeKit to control thermostats, usable as both a Python library and CLI, ideal for those avoiding Home Assistant. The scope is restrained and clearly documented; the limit is it only serves Ecobee users, and star counts don't yet show real installs.

Local Ecobee control in Python via HomeKit. No cloud, no ecobee API key, no Home Assistant. Pair once, then read/control temp, mode, sensors, and more from a GUI, CLI, or library.

#IoT#Self-Hosted#Privacy#CLI

★6

A

OpenVR-SpaceSync

shinyflvreC++

Aligns Lighthouse base station devices with a SLAM headset, continuously correcting optical tracking against the headset pose. Hybrid tracking is a hard VR problem few tackle seriously, and the approach is clear; but it only makes sense for a specific hardware combination and lacks build and test instructions.

Synchronizes Lighthouse devices with SLAM headsets using a Follow SLAM HMD mode that keeps the headset pose authoritative and continuously aligns Lighthouse tracking to it.

#Hardware#3D#openvr#steamvr

★17

A

opsflare

bearBoy80TypeScript

An unofficial Expo client for managing multiple Cloudflare accounts on mobile, genuinely useful for quick config changes on the go, and the description honestly notes OAuth requires deploying your own relay. Multi-account mobile tooling is largely unaddressed, so it's worth a look.

Unofficial Cloudflare multi-account client for iOS & Android (Expo). Unofficial Cloudflare multi-account mobile client. Usable with just an API token; OAuth requires deploying oauth-relay first and re…

#DevOps#iOS#Android#APIs

★21

A

smooth-swipe

cesp99C++

Adds a three-finger swipe desktop switch to KWin, bringing KDE gestures closer to macOS feel. Extremely narrow in scope and immediately noticeable after install, a typical plugin that does one small thing well; the limit is it only helps KWin gesture users.

A Kwin desktop-switching effect that makes the 3-finger swipe between virtual desktops feel like macOS.

#Linux#UI Design#Productivity#kwin

★13

A

cumulus

ascorbicTypeScript

A caching proxy for ATProto blobs running on Cloudflare Workers, a typical Cloudflare-ecosystem utility from an author with credibility there. Scope is clear and the description doesn't oversell; the limit is it only matters to people building Bluesky-related services on Workers.

ATProto blob proxy on Cloudflare Workers Cache

#APIs#Performance#Self-Hosted#atproto

★15

A

stripe-ksef

frogermcsTypeScript

Syncs Stripe EU B2B invoices to Poland's KSeF e-invoicing system, a very narrow but real problem, with honest configuration docs. Only useful to teams doing B2B in Poland with Stripe, but a rare open-source implementation of this kind of compliance integration.

Synchronize Stripe EU B2B invoices with the Polish National e-Invoicing System (KSeF) using Node.js and TypeScript

#Fintech#E-commerce#APIs#stripe#ksef

★11

A

trickshot

nathanliowTypeScript

Rebuilds the on-chain state of any Solana token and replays every operation a wallet performed on it, suited to on-chain forensics and reviewing anomalous trades. The idea is concrete and well-bounded, more substantive than a pile of sniper bots; but the repo is very new, with no evidence it runs or how deep support goes.

Rebuild any Solana token from the chain and replay what any wallet did on it.

#Crypto#Blockchain#Data Analysis#solana

★22

A

pio-ftdi

dpks2003C

Uses RP2040/2350 PIO to turn a microcontroller into an FT232H-compatible JTAG adapter, saving a dedicated chip; embedded debugging people will immediately see the value. The boundaries are clear; the limit is that speed and compatibility still need real testing.

Turn an RP2040 or RP2350 into an FTDI FT232H JTAG adapter, using PIO

#Embedded#Hardware#Debugging#rp2040

★7

A

godot-ui-integration

zimo-xiao-zhengPython

A Godot UI skill for Codex: generating editor-visible scenes from confirmed design mockups and running runtime visual consistency checks; the scope is narrow and inputs and outputs are clear, so anyone using both Godot and agents can try it today, at the cost of only working within the Codex combination.

A Codex skill for building Godot UI from approved designs with editor-visible scenes and runtime visual-parity checks.

#Agent Skills#Game Dev#UI Design#godot

★12

That's today. The other tiers and the boards follow.

BHas a spark66
  • B better-voice Combines screen context with voice dictation to address efficient mobile input; 111 stars in 0.7 days indicate real demand. It could be commercialized as an accessibility tool or integrated at the system level, competing with built-in dictation and third-party input methods, but requires continuous context understanding improvements. #Speech#AI#Multimodal

    Voice dictation with the screen context you point at.

    TarunTomar122Swift★111

  • B ua-skills Provides a real-time data-driven agent skill for mobile app paid growth, integrated via MCP; it addresses marketers' data decision pain. 46 stars is few but commercial value is clear as a SaaS service, competing with Amplitude and Mixpanel, with the MCP ecosystem as its differentiation. #Agent Skills#Marketing#MCP

    Agent skills for mobile app paid growth powered by real-time data with APPEEKY MCP.

    appeekyShell★46

  • B frontend-promotion-guard A frontend release gate integrating CSS integrity, style regression, and secure Docker deployment, addressing frontend release quality and plugging directly into CI; 42 stars is few but practical. Commercialization is enterprise DevOps services, competing with SonarQube and Lighthouse, requiring stronger integration. #Web Frontend#Testing#CI

    Release gate for CSS integrity, computed styles, visual regression, and safe Docker promotion.

    Reality-JHTypeScript★42

  • B rome An Agentic OS concept that merges the operating system with AI agents to address the future human-computer interaction paradigm. Its 64 stars in one day show early interest, but the prototype remains unclear; the path is to become the base layer for AI-native systems, though it needs massive investment and competes with OS-layer players like Claude and OpenAI. #AI Agents#Operating Systems#Open-Source Alternatives#grok#muse

    Rome is the agentic OS.

    rome-osTypeScript★64

  • B DYB-Pro It hands the protein design workflow to Devin for orchestration, automating wet-lab experiments and solving the efficiency of biotech iteration loops. Its 27 stars are few but technically leading; commercialization could be biotech SaaS or an internal tool, competing with traditional design software and AI4Science platforms. #Biotech#AI Agents#Science#ML Research

    DYB Pro hands the protein design pipeline to Devin: state a goal, add sequences, and an autonomous in-silico cycle returns a ranked, order-ready wet-lab shortlist at a fraction of the cost. Devin orch…

    yacine-baghliPython★27

  • B geofield-bracket Uses SE(3) equivariant field models to learn geometry, physics, and manufacturability to generate solver-validated brackets, addressing rapid engineering prototyping; 25 stars show early interest, but it could become a core CAD algorithm. Competitors are traditional FEA and generative design tools. #3D#ML Research#AI

    One learned latent for geometry + physics + manufacturability: give it a box and a load, get a solver-certified bracket. SE(3)-equivariant field model, immersed FEA, live 3D designer.

    connorkapoorPython★25

  • B susu-phone-agent Lets Claude Code control Android devices via MCP and Shizuku without root, addressing mobile automation pain and aiding accessibility; 24 stars but real demand. Commercialization could be device automation services, with competitors Appium and ADB, but MCP integration is the advantage. #MCP#AI Agents#Android#Automation

    Android device bridge for Claude Code via MCP + Shizuku. No root, no model polling.

    2005selene2005-a11yJava★24

  • B lemyloi-dichvideos A local-first video editor integrating ASR, OCR subtitle translation, and dubbing to address video translation needs; 35 stars in 1.9 days show interest, but competitors like Jianying and CapCut already cover this. Commercialization is via professional scenarios or private deployment, requiring distinctive features. #Video Editing#Speech#Video#AI

    Trình chỉnh sửa video local-first với ASR, OCR phụ đề gốc, dịch và thuyết minh.

    LexombienTypeScript★35

  • B FineConfiner2D A more stable bounds-confinement component for Unity 2D cameras, aimed at the common edge-clipping and jumping of Cinemachine Confiner 2D—anyone making 2D platformers knows the pain. Restrained in scope and honest in description, a clean small tool; limited to the Unity ecosystem, with little author reputation or usage evidence yet. #Game Dev#Games#unity#cinemachine

    A smarter alternative to Cinemachine Confiner 2D — no clipping, no jumps.

    rucchoC#★9

  • B write-notes-like-deepseek A decision record tool designed for AI agents, addressing the difficulty of tracing AI development decisions by depositing Agent Notes into repositories, fitting the AI engineering trend; star growth is steady and it could become a standard team practice. Commercialization is as a developer aid adopted by enterprises, with the main risk being its novel concept and unproven user acceptance. #Documents#Knowledge Base#AI Agents#Productivity

    Record Agent Notes the way the DeepSeek team does—decisions, trade-offs, and validation documented in one place, still traceable six months later. Can be layered onto any repository

    czm15053TypeScript★40

  • B MeterEye Uses an ESP32-CAM to read electricity meter LCDs without machine learning, addressing manual meter reading; 35 stars show the community likes such hardware projects. Commercialization is smart meter peripherals or home automation components, competing with ready-made smart meters that cost more. #Embedded#Hardware#Images#IoT

    A camera reads my electricity meter's LCD so I don't have to. ESP32-CAM + custom 7-segment decoder, no ML, no cloud

    epynicC★35

  • B super-beautiful-toast A Vue 3 toast library that turns the button you pressed into the notification itself, with spring animations and card stacking, zero dependencies. There's a clever touch in the interaction and the scope is restrained—a rare small-but-complete project; but toasts are extremely saturated, so it can only win on looks. #Web Frontend#UI Design#Animation#vue

    Toast notifications for Vue 3 where the button you pressed becomes the toast. Physical springs, a card-deck stack, no dependencies.

    srdavoJavaScript★11

  • B huashu-excel An Excel data-processing skill for AI agents covering the full workflow from cleaning to delivery, solving repetitive cleaning and reconciliation in data analysis, with a light openpyxl dependency for easy integration. Star growth reflects demand. It could become a standard component in agent ecosystems like MCP, with monetization in enterprise data analysis services. The risk is that tools like pandas are already powerful, so the "agent-ready" advantage must stand out. #Agent Skills#Data Analysis#Spreadsheets#Automation

    Full-process data analysis and Excel skill: inspect dirty tables, clean, align requirements, analyze, reconcile, deliver. Make the numbers AI computes stand up to scrutiny. Cross-agent universal, with…

    alchaincyfPython★40

  • B hono-shopify-auth Adds Shopify embedded app and webhook auth verification to Hono, one function solving one problem, exactly what Hono+Shopify developers lack. Scope is restrained and the description accurate; the limits are a narrow audience and the need to show how it differs from the official SDK. #SDKs#APIs#E-commerce#shopify

    Authenticate Shopify embedded app requests and webhooks in Hono

    besart-kTypeScript★6

  • B vanish A Garry's Mod server invisibility plugin that truly hides invisible players from the scoreboard, A2S queries, and client view, more thorough than typical admin mods. Only useful to GMod server owners, but the description and technical details are honest. #Games#Plugins#Game Dev#garrys-mod

    Server-side player hiding for Garry's Mod: a vanished player leaves the world, every scoreboard, status, server-side Lua and A2S, and clients see a real disconnect.

    ds-kimiLua★7

  • B apple-gpu-dvfs Reverse-engineers Apple Silicon GPU DVFS: voltage states, CLPC frequency control, and Metal benchmarks, a rarely touched low-level topic. It's research-flavored and not useful to ordinary developers, but worth reading as hardware performance reference. #Reverse Engineering#GPU#macOS#Hardware

    Apple Silicon GPU DVFS reverse engineering: voltage corners, CLPC frequency control, Metal benchmarks

    maderixObjective-C★22

  • B NasAnySim A self-hosted cellular gateway turning 4G modules and SIM cards into browser-accessible private phone and SMS services, addressing NAS users' remote communication needs; 30 stars show interest from a specific group. Commercialization could be hardware kits or software licenses, competing with commercial 4G gateways. #Self-Hosted#Hardware#Networking#Automation

    Self-hosted cellular gateway for NAS: turn a Quectel 4G module + SIM into a private phone & SMS service reachable from any browser

    mccdingShell★30

  • B standardassistant Gives each bot its own virtual display, mirroring the screen and forwarding input so agents can operate GUI programs like a human. This addresses the real conflict of multiple agents fighting over one screen; currently macOS-only and one day old, so stability remains to be seen in the code. #macOS#AI Agents#Automation#Multimodal

    macOS app giving each bot its own virtual display — mirrored live and driven by forwarded input

    UsefulSoftwareCoSwift★14

  • B open-source-5g-ntn-leo Adds a LEO satellite scenario to an open-source 5G NTN testbed, including propagation delay and Doppler tracking for a 600km orbit. A real addition for researchers doing satellite communication simulation, but the audience is tiny and the form is closer to paper companion code. #Networking#Science#5g

    LEO extension of the open-source 5G NR NTN testbed: full satellite pass with live propagation delay and Doppler tracking, 600 km orbit. Companion to open-source-5g-ntn.

    sabbir-uouluLanguage unknown★8

  • B BHUninstaller A cross-platform uninstaller explicitly benchmarked against Revo Uninstaller, selling itself on moving files to the recycle bin before deletion and letting you review why each file matched. The attitude is more cautious than similar tools, but claiming three platforms in two days strains credibility, and several open-source alternatives already exist. #Open-Source Alternatives#Windows#macOS#revo-uninstaller

    Free, open-source app uninstaller & leftover cleaner for macOS, Windows & Linux — a Revo Uninstaller / App Cleaner alternative. Nothing is ever deleted: every removal goes to the Trash behind a review…

    wpexpertinbdRust★21

  • B threetiles Aims to add 3D geographic tile rendering to Three.js, and people building web digital twins do lack a lightweight option; but the repo is under a day old with a single sentence, whether it can handle real tile data is unverified, and Cesium and 3d-tiles-renderer are ready competitors. #3D#Web Frontend#GPU#three.js

    3D Geospatial engine for Three.js

    zivTypeScript★18

  • B Nvidia-Tesla-v100-nvfp4-pcie A hands-on guide to running FP8/NVFP4 quantized models on two V100s without NVLink, spelling out three key changes and reporting 61–74 tok/s. Anyone still holding V100s can follow it directly; the limit is that it's a run log, not a general tool, and needs retuning when model versions change. #LLMs#GPU#Performance#Hardware

    Qwen3.8-27B in native NVFP4/FP8 on 2x PCIe Tesla V100-32GB (SM70): the PCIe runbook for v100-skinny + 1Cat-vLLM, with the 3 fixes that make it work without NVLink. 61-74 tok/s decode, MTP speculative …

    RedhatvaleShell★6

  • B fingerink.koplugin A plugin that lets old Kindles draw with a finger directly in KOReader, putting the touchscreen hardware to a new use; it's narrow in scope, honestly described, and works once installed. The audience is only jailbroken Kindle users and the features are limited, but it's the type that does one thing cleanly. #Plugins#Hardware#Linux

    KOreader plugin to draw on old kindles with fingers

    SMUsamaShahLua★11

  • B omarchy-tray A collapsible system tray for the Omarchy desktop that lets you drag any bar component into a drawer, with a clear scope and restrained QML implementation. It's plug-and-play for Hyprland users on that setup; the limit is that it's tied to Omarchy and meaningless on other desktops. #Linux#UI Design#Plugins

    A better Omarchy system tray: drag any bar widget into its slide-out drawer

    TyRichardsQML★21

  • B hermes-console A Flutter Android client for self-hosted Hermes Agent, packing chat, voice, and remote control into a phone; it only matters to people already running Hermes, shows no clear difference from the official interface, and 20 stars in a day proves little, so set it aside for now. #AI Agents#Android#Self-Hosted

    Android-first Flutter client for self-hosted Hermes Agent — chat, Bots, Voice and private remote control.

    xP3taDart★20

  • B dart-sdk-skills Turns the most easily misremembered Dart/Flutter details—SDK version constraints, minSdk mappings, widget migrations—into an agent skill, written by a Ruby community veteran. It saves people who write Flutter with Claude Code daily from repeated doc lookups; the limit is manual upkeep, so it goes stale with each SDK upgrade. #Agent Skills#AI Agents#SDKs#Android

    Agent skills for Dart & Flutter SDK versioning, language features, widget migrations, and minSdk lookups

    RandalSchwartzDart★15

  • B obs-mobcam-plugin A small plugin that turns Moblin into an OBS-usable camera; OBS plugins written in Rust are rare, and the author is Moblin itself. The audience is narrow, but it's the kind that does one small thing cleanly. #Streaming#Video#Plugins#obs

    Use Moblin as webcam in OBS.

    eerimoqRust★6

  • B overleaf-mcp Uses MCP to connect Overleaf Git projects to clients like Claude, letting paper writers have agents read and write tex directly. The niche is specific and the pain point clear; the limit is reliance on Overleaf's paid Git integration, and the star count is unverified. #MCP#Documents#AI Agents

    TypeScript MCP server for Overleaf Git projects

    fly233338TypeScript★6

  • B ai-watermark-remover Finds and strips hidden AI markers from your own text and files—invisible Unicode, C2PA/EXIF/XMP metadata—covering the overlooked side. The tool is clearly positioned, but removing C2PA raises compliance questions in some settings. #Watermarks#Privacy#AI#Documents

    Reveal & strip hidden AI marks - invisible Unicode, C2PA/EXIF/XMP metadata from text and files you own

    mohityadav8Python★11

  • B kindle-wall-display Turns a jailbroken Kindle into a low-power wall display that shows whatever PNG the server pushes, with a KUAL client and handwritten manual. The approach is honest and scope restrained; Kindle tinkerers can follow along. #Embedded#Linux#Hardware

    Turn a jailbroken Kindle into a low-power wall display that renders any PNG you serve it. Manual plus the KUAL client I run on mine.

    jstribletShell★13

  • B troposphere A self-hosted Ozone alternative for Coop, providing a content labeling service for AT Protocol and explicitly naming its target. It addresses the single-vendor lock-in of labeling services in the Bluesky ecosystem, niche but clearly directed. #Open-Source Alternatives#Self-Hosted#Social#ozone

    A self-hostable alternative to Ozone designed to work with Coop

    julietshenTypeScript★14

  • B Mars-Editor-APP A desktop app that converts Markdown writing into WeChat official account formatting and pushes it to drafts in one click. The need is real and the positioning is crisp, but this niche is already crowded by doocs/md, mdnice, and others, with nothing new apparent in formatting capability or workflow. #Documents#Content Writing#macOS#Windows

    Write in Markdown, convert to WeChat Official Account layout in one click, and push directly to drafts. macOS / Windows / Linux desktop app

    whyubel1eveTypeScript★18

  • B shell.online Generates a browser-accessible live link for any terminal process, useful for remote assistance or demos. The usage is one sentence and the need is real, but sshx, ttyd and tmate already do this, so the novelty lies only in implementation details. #Terminal#CLI#Self-Hosted#Networking

    A live browser link for any terminal process.

    TeoSlayerTypeScript★16

  • B TrueYZ A C/C++ implementation of Yaz0 compression that is byte-for-byte identical, with a name and description that state exactly one thing, showing the author knows what they're doing. Useful for people modifying old Nintendo game assets, but Yaz0 tools already exist, so the increment is limited and the audience tiny. #Reverse Engineering#Games#Embedded

    Byte-exact C/C++ Yaz0 compression.

    aboood40091C★8

  • B tikeytaka Stores Claude Code API keys in an "encrypted cloud sync, zero registration" vault and auto-injects them into projects. The pain point is real, but handing keys to a cloud service less than a day old can't prove its security; a local solution is safer. #Secrets#LLMs#CLI#Privacy

    Central API key vault for Claude Code — encrypted cloud-synced vault, zero sign-up, auto-wire keys into projects

    fivetakuShell★20

  • B jiditie A web mini-game simulating the crowded Guangzhou Metro Line 3, with a relatable premise and strong shareability, reaching thirty-plus stars in hours. Fun to click as a joke, but it offers no reusable technical content and will likely be forgotten once the hype fades. #Games#Web Frontend#Animation

    Subway squeeze mini-game: can you squeeze onto Guangzhou Metro Line 3?

    ns2250225TypeScript★36

  • B oil-skill-creator Treats Agent Skills as a product: create, review, remediate, and publish in one flow. The angle matches the current flood of Skills with uneven quality, so the direction is right; but the description is one sentence, with no visible process or outputs, so you must read in to see if it's prompt wrapping. #AI Agents#Agent Skills#Prompting

    Write Skills like a product: create, review, remediate, and release Agent Skills

    oil-oilPython★13

  • B tonghuasun-codex Connects local Tonghuashun market quotes and account data into Codex, which does hold appeal for A-share retail investors; but it doesn't clarify whether it reads the client or scrapes APIs, handing account info to an agent is risky, and it may vanish as fast as it appeared. #Fintech#AI Agents#APIs

    Connect the local 同花顺 quotes, account data and real-time data to Codex

    zhuyifangLanguage unknown★18

  • B Aletheia Decodes private proxy configs like .npvt, .slip, and .happ into readable formats and fixes an upstream bug that drops the WebSocket Host header, immediately useful to anyone holding such subscriptions and wanting to switch clients. Small scope, accurate description; but 6 stars at 0.3 days, compatibility and ongoing maintenance are still untested. #Reverse Engineering#Networking#CLI

    CLI decryptor for proprietary VPN/proxy config formats (.npvt, .slip, .ehi, .dark, .hat, .happ, .nm) — fixes upstream's dropped WebSocket Host header

    Arsham-xGo★6

  • B engine-sim-unity-audio Batch-converts Engine Simulator presets into a seamless engine-sound library usable in Unity, saving indie developers repetitive vehicle audio work. The pipeline is narrow and accurately described; the obvious limit is that it's useless without in-car engine sound, and it depends on two upstream projects. #Audio#Game Dev#3D

    Generate seamless Unity engine-audio banks from Engine Simulator presets.

    VangardoC++★16

  • B OpenCade Aims to be an open-source Fightcade alternative: a Tauri client plus Rust server, focused on clean-room rewritten arcade netplay. The gap is real since Fightcade is closed-source and Windows-only, but two days only builds a skeleton, with rollback sync and ROM compatibility still unaddressed. #Games#Networking#Open-Source Alternatives#fightcade

    OpenCade — open-source arcade netplay platform (clean-room Fightcade alternative). Tauri+React+TS client, Rust+Axum+Postgres server.

    ZendevveRust★19

  • B japan-deformed-map Compresses Japan's prefectures into a 28×25 grid of rectangles, output as CC0 SVG/JSON, saving a round of drawing for Japan-related data visualization. The assets are clean, but similar free maps are plentiful, making it a one-off resource. #Images#Data Analysis#Web Frontend

    A stylized map of Japan that simplifies prefectures into combinations of rectangles. 28×25 grid SVG and JSON assets (CC0 1.0)

    chizutodesignPython★10

  • B wasl Builds a prophet's genealogy on seven original Arabic sources, with each claim backed by machine-verifiable citation page numbers, turning textual scholarship into verifiable data. For developers it's just a data project; its value lies in the digital humanities citation model. #Knowledge Base#Science#Data Analysis

    Wasl — a verifiable genealogy (nasab) of the Prophet Muhammad, his household, the Sahaba and the Arab tribes, built directly on seven primary Arabic sources. Every claim carries a quotation machine-ch…

    hendrasaputraHTML★6

  • B 7032AltROMs An independent rewrite of the entire replacement ROM set for Fujitsu FM-7/FM77AV, MIT-licensed with public source, clearly scoped, a rare retro-machine preservation effort of real value to MAME users and old-hardware fans. The audience is very narrow, and 6 stars in 2 days shows it hasn't been widely verified on real machines or emulators. #Reverse Engineering#Embedded#Hardware#fm-7

    A set of alternative ROMs for the FM-7 / FM77AV series based on an independent implementation (MIT license, source published)

    7032JPAssembly★6

  • B dev-house Gives Claude Code a "dev team" with custom members, roles, skills, and permissions, running on a model of your choice. The one-liner states its purpose clearly and rides the multi-agent wave, but new implementations appear weekly, its own differentiator is unstated, and the stars came suspiciously fast. #AI Agents#LLMs#Collaboration#CLI

    Give Claude Code a dev team: members you create, on the models you choose, with their own roles, skills and permissions.

    SinghAbhinav04TypeScript★18

  • B chatgpt-local-supervisor-bridge Uses OpenAI's Secure MCP Tunnel to connect the ChatGPT web app to local project files, with an allowlist limiting what can be read. Anyone wanting the web model to read local code will be interested, but the core is just configuring the official channel, and the security boundary still needs your own review. #MCP#AI Agents#Secrets#Privacy

    A safe, allowlisted bridge from ChatGPT web to local project files through OpenAI Secure MCP Tunnel.

    VITASID57JavaScript★13

  • B github-agentscan-userscript A userscript that injects AgentScan information into GitHub user pages, written by a Vite team member, so code quality is probably reliable. But its value depends entirely on the external AgentScan service, and the audience is small. #Browser Extensions#AI Agents#github

    Show AgentScan info for GitHub users

    bluwyTypeScript★11

  • B Crestron3SeriesCLZBuilder A VS2022 tool for reproducible CLZ packaging on Crestron 3-series controllers, with official signing and optional SIMPL+ modules. It solves a very specific pain in the AV integration industry and describes itself honestly; but the audience is in the thousands and the docs are one paragraph. #Build#Windows#crestron

    Crestron 3-Series CLZ builder for VS2022 with reproducible SIMPL# packaging, official signing, optional SIMPL+ modules, and 4-Series outputs.

    srichardscPython★11

  • B super-terrain A grid terrain editing library for three.js. The direction is clear, but the three.js ecosystem already has many terrain and editing tools, and the description doesn't explain the editing approach or performance trade-offs, making it hard to tell how it differs. #Web Frontend#3D#Game Dev

    mesh terrain editing for threejs

    vibe-stackTypeScript★13

  • B Redstone Brings redstone circuits into a PocketMine-MP Bedrock server, requiring its own implementation of signal strength and update order, which is hard work; a must-have for server owners running Bedrock who want redstone. Scope is restrained and the description doesn't oversell, but 8 stars in two days hasn't proven mechanism coverage, and matching Java Edition behavior is the biggest test. #Games#Plugins#Game Dev#minecraft

    PocketMine-MP plugin bringing redstone mechanics to your server.

    CosmoversePHP★8

  • B Context-Bolt A Chrome extension that moves AI conversations from ChatGPT to Claude in one click; the idea is practical, but many similar export/transfer tools already exist and only the interaction differs. Privacy-first is a plus, but at 6 stars it's unclear whether it actually works. #Browser Extensions#LLMs#Privacy

    Capture any AI conversation and carry it to another LLM — one click. A free, open-source, privacy-first Chrome extension for ChatGPT, Claude, Gemini & DeepSeek.

    anshvarshney1502TypeScript★6

  • B workout-guide 302 openly licensed fitness exercise illustrations plus a framework-agnostic npm package, saving fitness app developers a round of image hunting. It's still essentially an asset library rather than a tool, and you need to check samples to see if the style fits. #Health#Images#SDKs

    302 open exercise illustrations and a framework-neutral npm package by Bryl Lim

    bryllimAstro★20

  • B pi-openai-web-search Wraps OpenAI's web_search (Codex protocol) as a callable tool in a pi extension, with small code, a single goal, and an accurate description. A handy step for pi users, but not much beyond that. #Plugins#AI Agents#APIs#LLMs

    pi extension: OpenAI web_search (Codex protocol) as a model-callable tool

    linearuncleTypeScript★16

  • B WPA4 Claims to be an experimental implementation of WPA4 "MegaPlan" and states plainly in the description that it is non-interoperable, non-compliant, and unfit for production networks. The honesty is commendable, but with no interoperability its practical use is near zero—more a concept demo. #Network Security#Privacy#wpa4

    This is an **experimental, non-interoperable** open-source implementation of the WPA4 MegaPlan. It is NOT a certified standard, NOT ready for production networks, and NOT interoperable with real WPA3/…

    vantamothlabs-ossPython★7

  • B H.E.R.A. Runs YOLOv8 segmentation plus HSV tissue analysis offline on-device to produce wound assessments and PUSH scores, chaining model, color analysis and decision rules. The direction is concrete, but medical conclusions need datasets and validation, so it currently reads more like a competition entry. #Health#ML Research#Embedded#Multimodal

    H.E.R.A. (Healing Evaluation and Recognition Architecture) — an on-device edge-AI system for offline wound assessment using YOLOv8 segmentation, HSV tissue analysis, and PUSH-based decision logic.

    SyueFaDart★8

  • B project-celestia A Three.js viewer for PNG layer coordinates and attributes, described in Spanish, possibly handy for developers slicing 2D game art. The feature set is narrow but described concretely; the limits are a small audience and no sign of maturity beyond the description. #3D#Web Frontend#Game Dev#Images

    Project Celestia | Visor de Coordenadas y Propiedades para Capas PNG | Three.js + JavaScript | Medición exacta de Posición, Escala, Rotación, Opacidad y Curvatura en tiempo real | Herramienta técnica …

    andrea-lopez-devJavaScript★7

  • B generate-ai-presentations-skill A skill pack for Codex that generates 16:9 slide images, PPTX files, and storyboard tables, with a clear use case. But it essentially chains existing image and PPT generation, has many alternatives, and the repo doesn't show output quality. #Agent Skills#AI#Presentations#Image Generation

    Codex Skill for creating 16:9 presentation images, PPTX decks, image prompts, and slide planning tables.

    hsuliangLanguage unknown★16

  • B re-goldsrc-won-launcher-1792 A source-level reconstruction of the WON-era Half-Life launcher build 1792, game-preservation reverse engineering. The goal is restrained and the claims honest—a small thing done thoroughly; but very few can use it, and build and verification methods aren't explained. #Reverse Engineering#Games#Windows#half-life

    Source-level reconstruction of the WON-era Half-Life launcher, build 1792.

    oxiKKKC++★6

  • B TRaIL-Odom A tightly coupled radar-IMU-lidar odometry that uses adaptive Doppler weighting to handle LiDAR degradation in low light and smoke, directly readable by SLAM researchers; acceptance by RA-L shows the method has been reviewed. The limit is that the repo looks like a paper appendix, and it's unclear whether reproducible experiment configs are released. #Robotics#ML Research#Science

    [RA-L 2026] TRaIL-Odom: Tightly Coupled Continuous Time Radar-IMU-LiDAR Odometry with Adaptive Doppler Weighting

    ChiyunNohLanguage unknown★10

  • B vision-exp-tile A DSH plugin that slices large images into 800×800 tiles, labels coordinates, and aggregates results, targeting the old problem of vision models reading large images at insufficient resolution. The description is concrete with clear boundaries, even noting it doesn't count costs; the limit is it's tied to DSH and specific models. #AI#Multimodal#Images#Plugins

    DSH plugin: split large images into 800×800 lossless tiles + coordinate annotation + tile aggregation logic, directly connected to deepseek-v4-flash-vision-exp for recognition; uses only pure official…

    Nicholas023JavaScript★10

  • B smart-brief Uses Claude Code skills and hooks to replace built-in Artifacts with a version-manageable local HTML decision brief, suited to small teams needing records. The approach is concrete and the boundaries clear, but it only serves Claude Code users, and the alternative is committing markdown straight to the repo. #Agent Skills#AI Agents#Documents

    A Claude Code skill and hook that replace the built-in Artifact tool with local, version-controlled HTML decision briefs.

    WatsonTsaiHTML★8

  • B DeepSeek-Whale-widget-desktop Turns your DeepSeek account balance into a little desktop whale widget, a clean small tool, but it only serves DeepSeek API users, shows a single number, and would take a few dozen lines to write yourself. #AI#Windows#Monitoring

    DeepSeek balance little whale standalone desktop version

    comreade-123JavaScript★22

  • B nvmman An interactive nvm manager written in Rust that can migrate global npm packages and maintain a local registry, with concrete features. But nvm/fnm/volta already cover most cases, and the only addition is a TUI experience. #CLI#Terminal#Productivity

    Rust TUI NVM Manager - Manage Node.js NVM versions and NPM packages - Interactive nvm maintainer: installs and verifies native platform-specific latest Node LTS, migrates global npm packages, keeps a …

    handyutilsRust★15

  • B YapJail A Discord bot that throws members into "yap jail": no text or voice, but camera and screen share stay on. The idea is fun and the implementation simple, suited only to hobbyist self-hosted communities with no general value. #Social#Automation#Speech

    A Discord bot that puts users in "yap jail" - preventing them from speaking in voice channels and chatting while allowing camera and screen sharing!

    imaketech1Python★18

  • B -1m-mail A self-hosted temporary email service built on Cloudflare Workers + D1 + Email Routing, deployable to your own domain in one click, a practical engineering combination. But there are already many open-source temp mail implementations; the differences are mainly appearance and burn-after-reading details. #Self-Hosted#Email#Privacy#cloudflare

    Free temporary email: generated in 1 second, no registration, burn-after-reading, auto-destroyed on expiry. Built on Cloudflare Workers + D1 + Email Routing, deployable to your own domain with one cli…

    linxk8HTML★17

  • B hazel A read-only database monitor for the Omarchy status bar, covering Postgres, MySQL, ClickHouse, and more. Restrained in scope and accurately described, but the audience is doubly limited by Omarchy and QML, so it's of little use outside that desktop. #Monitoring#Databases#Linux#omarchy

    A polished, read-only PostgreSQL, MySQL, MariaDB, Percona, and ClickHouse monitor for the Omarchy bar.

    ryrobesQML★7

COrdinary89
  • C KUMA-DefuzeX A proxy behavior testing SDK that allows simulating and verifying agent behavior, addressing AI agent testing challenges; 39 stars held steady over 2.2 days, indicating research-oriented demand. Commercialization is as an AI engineering testing tool, but competitors like LangSmith require differentiation. #AI Agents#Testing#SDKs

    Python SDK for DefuzeX agent behavior testing.

    DefuzeX-AIPython★39

  • C WNM-3D A 3D world navigation model for vision-language navigation, addressing embodied intelligence navigation; 58 stars indicate academic interest, but it is strongly research-oriented and hard to apply directly. Commercialization is licensing to robotics or autonomous driving, requiring extensive validation, competing with related SOTA models. #ML Research#AI#Multimodal#3D

    Official Implementation of "WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN"

    TeleHumanPython★58

  • C canopy A modular GitHub Actions runtime providing custom execution environments, addressing actions dependency locking and limited flexibility; 36 stars show niche demand, but it could serve as a CI platform extension point. Commercialization requires partnering with GitHub, competing with act for local runs, and needs to be more powerful. #CI#Build#Automation#DevOps

    Modular runtime for Github actions

    ferranbtRust★36

  • C MK-GCash-Link-OpenSource A GCash link workspace with a local web UI, but memory-only storage means data is not persisted, limiting practicality; fast star growth may reflect payment integration hype. Commercialization is payment integration tools for Philippine developers, but compliance and payment security are key, with the risk being fierce competition and money-sensitive issues. #Fintech#Scams#Automation

    Standalone, memory-only GCash link workspace with a local web UI.

    mika50000Python★51

  • C deepseek-v4-flash-vision-video-rag Indexes video frames for Q&A, with answers carrying [MM:SS] timestamps and generating playable clips plus an HTML keyframe verification page, more thoughtful interaction than most video RAG. But it's tied to a possibly unavailable DeepSeek vision model, and the naming is marketing-flavored. #RAG#Video#Multimodal#AI Agents

    DeepSeek V4-Flash Vision Video RAG lets AI truly "understand" a video, then you ask it questions: it tells you the answer, at which minute and second the answer occurs, and cuts out a playable clip an…

    liangdabiaoPython★9

  • C taskii A terminal task/note/focus panel written in Go with Bubble Tea. The direction is clean, but TUI todo apps are saturated and it solves no new problem; good for reading Bubble Tea examples, but no reason to pick it as a daily tool. #CLI#Terminal#Productivity

    TASKII - A terminal dashboard for tasks, notes, and focus, built with Go and Bubble Tea.

    parsaenamiGo★19

  • C walgit A new Rust repository from a well-known author, seven hundred-plus stars in half a day, but the description is empty—nobody knows what git variant it is or what problem it solves. The author's reputation is worth waiting on; today, clicking in means guessing intent from code. #CLI#Build#git

    tobiRust★764

  • C AMA An implementation of multi-agent adaptive memory from an ACL 2026 Findings paper, of some reference value to researchers working on long-term agent memory. But the repo only has the paper's same-named code, lacking reproduction notes and datasets, so industry can't use it until someone gets the experiments running. #LLMs#AI Agents#ML Research#RAG

    Official implementation of AMA: Adaptive Memory via Multi-Agent Collaboration (Findings of ACL 2026)

    SherlockwzPython★7

  • C Kinect-Xbox-360-Remold Aims to make the Xbox 360 Kinect usable again on modern Windows/Linux, with driver runtime and an app suite. Reviving old hardware is a real need, but libfreenect and similar already exist, the repo is two days old, code depth is unclear, and the slogans outrun the progress. #Hardware#Windows#Linux#Reverse Engineering

    A Windows/Linux driver-runtime and application suite for **Kinect for Xbox 360 / Kinect 1414**.

    SpidougProcessing★7

  • C sedona-sunset A first-person walk through Sedona's red rocks generated entirely in code, with meshes, textures and audio all procedural rather than external assets, making it an interesting procedural scene sample. But it's more a personal sketch than a tool, and offers no reusable generation approach. #3D#Game Dev#Animation

    A first-person walk up a dry wash between red rock buttes in Sedona at golden hour. Every mesh, texture and sound generated procedurally in code — zero external assets.

    StarKnighttJavaScript★13

  • C Triad Has multiple agents divide engineering work, with none allowed to sign off on their own designs, and includes a ledger from actual runs. The separation-of-duties angle is more interesting than typical multi-agent frameworks, but the description is convoluted and the structure unclear, so it's hard to see how to integrate it. #AI Agents#LLMs#Collaboration#Testing

    A setup that lets multiple AI agents collaborate on engineering work, where no party can sign off its own design as passing, plus its implementation and the ledger left behind when it actually ran.

    Wu030616C#★13

  • C grokbot-cloudflare-inbox A self-hosted Grok Bot inbox template based on Agentic Inbox, running on Cloudflare Workers. It gives people wanting to tinker with a bot inbox a starting point, but at 0.4 days with no usage validation, it looks more like a template copy. #AI Agents#Self-Hosted#Email

    Public GitHub template for a self-hosted Grok Bot inbox on Cloudflare Workers, based on Agentic Inbox.

    ethanolivertroyTypeScript★14

  • C omarchy-which-key Adds which-key key hints to Omarchy (a Hyprland distro), by a well-known developer, with small, complete code and a clearly scoped purpose. Only meaningful for Omarchy users; others can't install it. #Linux#CLI#UI Design

    Which-Key for Omarchy

    huacnleeShell★14

  • C A-Pilot-Quant-Deployment-for-Edge-MoEs Quantization and deployment experiments for edge MoE models like MiniCPM-MoE, a concrete direction; but it's only called a pilot with no accuracy, latency data, or usage steps, so for on-device inference people it currently reads like a paper's companion draft. #ML Research#Performance#GPU

    A Pilot Quantization and Deployment on Popular Edge MoEs like MiniCPM-MoE

    zhengzihaoPKUC++★13

  • C CSDL3 An object-oriented C# wrapper for SDL3 and its companion libraries, saving people who write cross-platform games or tools in C# from hand-writing P/Invoke. Clear scope and honest description, but similar bindings (SDL3-CS and others) already exist, differing only in API style; 6 stars at 1.4 days, coverage unproven. #SDKs#Game Dev#Windows

    A modern, object-oriented C# wrapper for SDL3 and its official satellite libraries

    AtompapstC#★6

  • C KanagawaWin11 A small theme pack bringing the Kanagawa color scheme to Windows 11, aimed only at desktop-tweaking fans of that palette. The description is honest and not overstated, but similar ports are already plentiful on GitHub; worth a glance if you want a new color scheme. #Windows#UI Design#Productivity

    Kanagawa theme for Windows 11

    MrDLingtersCSS★7

  • C pi-nvim-review Sends line-based review comments from Neovim to a running Pi session, solving the small pain of giving agent feedback inside the editor. The feature is simple and clear, but it depends on Pi and has a very narrow audience. #Editors#Plugins#AI Agents

    Send line-based Neovim review comments to a live Pi session

    jillesmeLua★6

  • C bisca A self-hosted card table where Claude sits in to play Monopoly, Dou Dizhu, and UNO with people, positioned as family entertainment rather than a tool. Multiple game implementations show the author really built something, but AI play quality and rule correctness are unaddressed; similar LLM companion projects are common lately, and 12 stars aren't enough to prove it's more fun than existing options. #Games#AI Agents#Self-Hosted#LLMs

    Self-hosted game den where AI players pull up a chair — Monopoly/大富翁/Doudizhu/Zha Jin Hua/UNO with Claude at the table. A self-hosted home card den where a set of AI card buddies play at the same tabl…

    29-CuJavaScript★12

  • C dsh-lowtide Time-shifted task delegation for DeepSeek Harness: queue jobs when idle, run them unattended in off-peak hours, then check the report. The idea is concrete and exploits off-peak quota, but it only works for dsh users and never explains what happens on scheduling failure or quota changes. #AI Agents#LLMs#Scheduling

    Time-shifting task delegation for DeepSeek Harness (dsh): plan tasks at leisure, they run unattended off-peak, come back to a report. Human-adjudicated, desktop + web.

    KelaoHuTypeScript★9

  • C telegram-webproxy-installer A one-click script to install multi-instance MTProxy with Caddy on Debian/Ubuntu, saving effort for people self-hosting Telegram proxies. The problem is that many similar one-click scripts exist, differing only in multi-instance and TLS; script projects also need long-term maintenance. #Network Security#Self-Hosted#DevOps#telegram

    One-click multi-instance Telegram web proxy installer (MTProxy + Caddy) for Debian/Ubuntu servers.

    MNSH-NexoShell★9

  • C tg-web-proxy Packages telegramdesktop's tproxy-server into a Docker stack with a site directory and docs, making it easy for non-tinkerers to self-host a Telegram Web proxy. It's a single clear task, but essentially someone else's code plus a deployment layer; the upstream repo is the alternative. #Networking#Self-Hosted#DevOps#Privacy

    Telegram WEB proxy deployment: Docker stack, site catalog, and docs (based on telegramdesktop/tproxy-server)

    RTHeLLJavaScript★13

  • C dataglot A federated SQL query engine in Rust that pushes governance policies into the execution plan, connecting all databases through one Postgres endpoint. The direction is clear, but it faces mature projects like Trino and Steampipe, and a 0.9-day-old repo currently reads more like a manifesto. #Databases#APIs#Data Analysis#Performance

    Rust-native federated SQL query engine with governance enforced in the query plan. One PostgreSQL endpoint for all your databases.

    dataglotaiRust★9

  • C vocab-passport Offline root-word flashcards for the FoloToy AI Passport hardware, implemented in C and runnable offline, with a very specific target. Only owners of that hardware can use it, and both code size and docs are limited. #Embedded#Learning#Hardware

    Offline word-root flashcards for FoloToy AI Passport | Offline word-root flashcards for FoloToy AI Passport.

    joeseesunC★7

  • C lw.MD A local Windows Markdown editor packaged as a single portable EXE with React + Vditor + WebView2, clearly positioned. Similar tools like Typora and MarkText already exist, unless you specifically want single-file distribution. #Windows#Editors#Documents

    A clean and reliable local Markdown editor for Windows, built with React, Vditor, C++17 and WebView2, distributed as a single portable EXE. A clean and reliable local Markdown editor for Windows, buil…

    lxw112190C++★7

  • C sleep-toggle-menu A native Swift menu bar app that toggles whether a MacBook sleeps with one click, explained in a single sentence. Similar tools are plentiful, so it only matters if you need exactly this switch. #macOS#Productivity#UI Design

    A macOS app that toggles whether a MacBook can sleep from the menu bar

    minorun365Swift★6

  • C SonicAdvanceRecomp A static recompilation project for the GBA game Sonic Advance. Recompilation has precedent, and applying it to GBA is still uncommon; but the repo has only a title, no build progress or runnable output, so for now it's a placeholder. #Game Porting#Games#Reverse Engineering#gba

    Sonic Advance Recompilation Project

    smiluredevC★8

  • C cassette-futurism Generates cassette-futurism, terminal-style wallpapers and macOS icons, a very small scope but clear about its audience: people who like this aesthetic can use them as assets. The implementation isn't novel; all the value is in whether the style suits your taste; 6 stars at 0.6 days, and no sample images in the repo. #macOS#Images#UI Design

    Procedural wallpaper and macOS icon generator in the cassette futurism / terminal-UI style.

    GallyfreianPython★6

  • C toolshed A tool-schema proxy for Hermes that compresses the overhead of repeated tool descriptions and restores them on demand, targeting a specific problem in the agent context. Only meaningful to Hermes users, and with no measured token-savings data, it can only be treated as an idea for now. #AI Agents#LLMs#Performance

    An adaptive tool-surface proxy for Hermes — reduces repeated tool-schema overhead while preserving on-demand recovery

    Huy3koPython★10

  • C repo-evolution-visualization-skill An agent skill that turns commit history, star curves, and contributor relationships into hand-drawn-style dashboards and videos, a likable idea for project retrospectives or launch material. But the output is presentational, data definitions and implementation details are unstated, and it shipped on day one, so maturity is doubtful. #Agent Skills#AI Agents#Data Analysis#Video

    Generates a highly reusable, hand-drawn doodle-style interactive web evolution dashboard and showcase video from any Git repository history, GitHub star growth curve, contributor rings and milestones

    SXP-SimonHTML★10

  • C momentum-trading-backtester- A momentum strategy backtester with statistical tests and a Streamlit dashboard. The approach is fairly rigorous, but it's a common personal quant project with no unique data source or method; similar backtesting frameworks are a search away. #Fintech#Data Analysis

    Momentum investing strategy backtester with statistical validation and interactive Streamlit dashboard

    utplawanPython★10

  • C adonis-llm-boilerplate An LLM app scaffold from the author of AdonisJS that sets up project structure and common integration patterns. It saves a bit of startup time for people familiar with the framework, but a scaffold's value ends once you're started, similar templates are plentiful, and it offers no new approach. #LLMs#AI Agents#Build#Web Frontend

    RomainLanzTypeScript★23

  • C Brawl-Spectator Uses Frida to modify the Brawl Stars client for spectating by tag, which bypasses game restrictions and may break whenever anti-cheat updates. Interesting to Frida reverse-engineering fans, but not something to recommend. #Game Cheats#Games#Reverse Engineering

    A Brawl Stars Frida mod for spectating players by tag, with support for both normal spectating and Brawl TV spectator mode.

    byRyoJavaScript★11

  • C cua-lite Another wrapper claiming to "make computer-use agents simple," slogan first; it's unclear how it differs from browser-use or OpenAI CUA, and it doesn't say which environments are supported or how to install it. #AI Agents#Automation#LLMs

    CUA-Lite: Computer-Use Agents Made Simple

    cua-litePython★17

  • C auth-center Another Spring Boot IAM/RBAC authorization platform with a full stack and feature list, but it never explains how it differs from existing options like Keycloak or Casdoor. Only worth a look if you specifically want a Spring ecosystem template. #Self-Hosted#App Security#APIs

    Authentication middle platform service: a unified authentication and authorization platform (IAM/RBAC) for multiple monolithic applications and microservices. Built on Spring Boot 3, Spring Security, …

    haishishushuJava★18

  • C Low-Spec-Niri-Dotfiles A niri desktop config for low-spec machines, claiming about 230MB idle usage and using matugen to derive colors from the wallpaper. Useful reference for Wayland tinkerers, but dotfiles are essentially a personal environment snapshot, so copying them means readjusting yourself. #Linux#UI Design

    Lightweight niri desktop: ~230 MB idle, wallpaper-driven Material You theming via matugen.

    okyashgajjarShell★8

  • C wintilex An automatic tiling window manager for Windows implemented in Rust. The ecosystem already has mature projects like komorebi and GlazeWM, while this repo offers only 'fast and modern' with no evidence of differentiation or stability. #Windows#Productivity#Automation

    WinTilex is a fast and modern auto-tiling window manager for Windows.

    wintilexRust★15

  • C verify-regression-tests The angle of 'verifying whether regression tests actually flip because of the target bug' is more specific than its batch siblings, but it's still just skill text with no runnable implementation or evaluation cases. Wait until there are signs of real use. #AI Agents#Agent Skills#Testing

    Open Agent Skill for Claude Code and Codex that verifies whether a regression test fails for the intended bug and passes with the candidate fix—catching false greens caused by mocks, gates, fallbacks,…

    aiopshwangPython★8

  • C fifty-nifty-circuits A collection of papers and posters on fifty two-transistor circuit variants, useful for circuit teaching and inspiration. But it's reference material rather than a tool, so software developers will rarely need it. #Hardware#Embedded#Science

    Paper and posters showcasing fifty nifty variations of two-transistor circuits

    iic-jkuTeX★6

  • C vibe-flow Hold-to-talk with a Bluetooth voice remote on Windows, turning speech into code descriptions or AI commands. The input method is interesting, but the text is all marketing, with no recognition approach, latency, or compatibility details, so the actual experience is unpredictable. #Speech#Productivity#Windows#AI

    Vibe Flow is a low-cost Vibe Coding tool built specifically for Windows. Just connect a Bluetooth voice remote to quickly do Chinese and English voice input, code descriptions, and AI commands by hold…

    richlearntodo-debugC#★10

  • C dsh_theme_terraria A single HTML file that reskins the DeepSeek Harness coding console with a Terraria pixel theme, zero dependencies, so you can see the effect as soon as it's installed. A nice little bonus toy for heavy users of this tool, but it's essentially a theme skin that changes no workflow; the dsh ecosystem already has more than one reskin plugin. #Plugins#UI Design#Terminal

    Turn the DeepSeek Harness AI coding console into a Terraria pixel world—a guide accompanies you as you write code, with real conversations, tool approvals, and difficulty switching, in a single file w…

    10086ggqqHTML★16

  • C OpenNomi An AI companion client for iPhone using the Xiaozhi protocol, implemented in SwiftUI. AI companion apps are highly homogeneous, and the repo doesn't explain character design, voice capabilities, or differences from hardware counterparts. #AI#iOS#Speech

    An expressive AI companion client for iPhone, built with SwiftUI and the Xiaozhi protocol.

    kerwinyoung77Swift★7

  • C SafeGenerator A single-file, offline, auditable BIP-39 mnemonic generator with an honest premise: no network, no dependencies. But generating seed phrases in a browser is itself high-risk, and the repo doesn't discuss randomness sources, side channels, or offline verification; mature offline alternatives already exist. #Crypto#Secrets#Privacy

    Software autocontenido en un único archivo HTML, sin dependencias ni conexión de red, que implementa el estándar BIP-39 de forma determinista y auditable.

    IngenieroSeedHTML★11

  • C Douyin-Liquid-Glass A Kotlin tweak giving Douyin's bottom bar a liquid glass effect, essentially UI beautification. Somewhat useful for people wanting to restyle the client, but it's tightly coupled to Douyin versions, breaks easily, and isn't a reusable component. #Android#UI Design#Productivity

    Liquid Glass For Douyin. Douyin bottom bar liquid glass

    YuanhaoBeiKotlin★22

  • C EraLife One line describes an 'ever-evolving life simulation,' with no visible gameplay, architecture or runnable content, and GDScript only matters to Godot players. Sixteen stars in one day looks like social spread; there's nothing to evaluate yet, so wait for a playable demo. #Games#Game Dev#3D

    A continously evolving life simulation built around a world that exists beyond a single player.

    acrello-sudoGDScript★16

  • C huashu-gpt-image A GPT-image prompt methodology plus playbook whose value depends on the author's personal feel and can't be verified like a tool. Worth browsing to learn image prompting, but free similar content is everywhere, so it's more a bookmark than an engineering asset. #Prompting#Image Generation#AI

    Prompt engineering methodology for GPT-image-2. Core: replace adjectives with real reference names, and default prompts to short Chinese sentences. Includes a single-image playbook, batch grid generat…

    alchaincyfPython★9

  • C markdown2site A zero-config generator that turns Markdown into docs sites, blogs, and landing pages, a space already served by mature options like VitePress and Astro. The repo doesn't state its differentiator, and "production-ready" is just a slogan. #Web Frontend#Build#Documents

    Build production-ready documentation sites, blogs, and landing pages from markdown with zero build configuration.

    imaketech1JavaScript★17

  • C atelier-lab A glassmorphism-style Obsidian vault template with reading tracking, a job-hunt kanban, and a three.js background. Visually thoughtful, but essentially a personal config share—what you get depends on filling it yourself, and similar vault templates are already plentiful. #Knowledge Base#Productivity#UI Design

    A cinematic, dashboard-first Obsidian vault — glass bento dashboards, Open Library reading tracker, career pipeline, and a three.js lo-fi workspace. MIT.

    novel-byteJavaScript★13

  • C vocacolle-anti-jogai A small script for VocaColle submitters to cancel an event's exclusion of their work. A gray-area tool that works around platform rules, limited to the Japanese Vocaloid scene, with almost no transferable technical content. #Browser Extensions#Audio#vocacolle

    VocaColle exclusion cancel script

    sevenc-nanashiTypeScript★16

  • C LoverConnect-Enhanced Turns Android phone status into MCP tools fed to an AI assistant, stressing that location broadcasting requires the owner's consent and data stays local. The direction is reasonable, but the description stops at a feature list without explaining installation or what it works with; similar "phone MCP bridges" already exist, and 15 stars in a day doesn't reveal implementation depth. #MCP#Android#Privacy

    LoverConnect enhanced Android MCP tool: phone status awareness, voluntary safe location broadcasting, and local privacy protection.

    AZHi-xinxinKotlin★15

  • C data-analysis-ml-agent-skills Another 'evidence-first' agent skill collection that is really prompts and process docs rather than a verifiable tool, and dozens of similar repos appear weekly. The author opened five near-identical repos at once, which looks more like placeholder volume. #AI Agents#Agent Skills#Data Analysis

    Evidence-first AI agent skills for reliable data analysis, machine learning, model validation, and reproducibility.

    aiopshwangPython★8

  • C hermes-conductor Claims to be a production-grade multi-CLI orchestration pattern set, but it's all methodology and kanban stories, with no clear deliverables or minimal example; 29 stars in half a day doesn't match the content's heat. #AI Agents#LLMs#Automation#CLI

    One Hermes conductor. Many coding CLIs. Zero trust in self-reports. Production multi-harness orchestration patterns: worktree lanes, verification gates, recovery playbooks — from 18 kanban boards and …

    forcewakeLanguage unknown★29

  • C HDT The official implementation of a multi-objective recommendation paper using a hierarchical decision Transformer. It's research reproduction code, useful only to researchers in that direction, with limited engineering applicability. #ML Research#AI#Data Analysis

    Official code for Sparks of Surprise: Multi-objective Recommendations with Hierarchical Decision Transformers.

    jieWANGforworkPython★6

  • C gjc-agy-skill A Korean-language skill pack for the Antigravity CLI covering vision/OCR, image generation, and print-mode recipes, plus hands-on pitfall notes. Its audience is Korean users of that specific CLI, hard for outsiders to reuse. #Agent Skills#CLI#Image Generation#AI

    GJC(가재코드) skill — Antigravity CLI(agy) integration: vision/OCR, image generation, print mode recipes. Includes a pitfalls document based on real measurements

    jkf87Shell★14

  • C DSH-Brain-Bridge Uses MCP to connect the DeepSeek Harness agent to the ChatGPT web version as an external reasoning backend, an assembly-style approach. The idea is concrete but only meaningful to people using both products, and it depends on web-end behavior, so stability can't be judged; 6 stars at 0.7 days, too early to tell if it will last. #MCP#LLMs#AI Agents

    A strict MCP reasoning gateway that connects DeepSeek Harness agents with ChatGPT Web as an external reasoning provider.

    2025ashoreJavaScript★6

  • C biblia.publica A repo organizing Brazilian Portuguese public-domain and CC-licensed Bible translations, with decent handling of formats and licensing, handy for anyone doing Portuguese corpus work. But it's ultimately a data compilation rather than a tool, with no technical substance of its own. #Documents#Knowledge Base#Learning

    Repositório dedicado à organização de traduções bíblicas em português brasileiro disponíveis em domínio público ou sob licenças Creative Commons.

    Projeto-EuaggelionPython★9

  • C auto_aim_rps26 RoboMaster outpost auto-aim code that is a team-internal vision solution rather than a general tool, useless to outsiders; such auto-aim code also often sits in a gray zone of competition rules. Technical details are unstated. #Robotics#Game Cheats#Games

    RPS team outpost and other aimbot code

    aiyo472C++★10

  • C cbmman A TUI manager for a project called cbm (Codebase-Memory-MCP), whose value depends entirely on another niche tool. The README never explains what cbm is, so outsiders can't get started. #CLI#Terminal#MCP

    Codebase-Memory-MCP Manager CLI TUI to interactively manage cbm projects, artifacts, server.

    handyutilsShell★18

  • C TwhWiki Aims to turn scattered diaries into an indexable life map, an appealing concept. But the description stops at vision, without clarifying input format, indexing method, or final output, so it reads more like a personal project. #Knowledge Base#Documents#Productivity

    the-way-here: turn scattered diaries into an indexable map of your life.

    lihaozheCharliePython★13

  • C spotless One line says it keeps the Downloads folder clean, but not whether it archives on a schedule, sorts by type, or is pure CLI, nor which platform it runs on. Hazel and organize-downloads already cover this need, with no new approach visible; ten stars in two days isn't worth ten minutes. #Productivity#Automation#Downloaders

    keep your downloads folder spotless

    ripgrimTypeScript★10

  • C Dwarfipedia A viewer for Dwarf Fortress legends mode with a loud title, but no screenshots, no word on which save formats it supports, and no comparison with existing legends viewers. DF players do need better viewers; this one hasn't shown it is one. #Games#Data Analysis#dwarf-fortress

    A legends viewer like no other!

    thatchworxPython★9

  • C pagiera A full-stack visual site builder for React/Next.js. The space already has mature options like Builder.io, Plasmic, and Webstudio, while this offers only a one-line positioning with no demo and no word on export or code ownership, making its value hard to judge. #Web Frontend#UI Design#Editors

    A full-stack visual website builder for React and Next.js.

    voilabsTypeScript★6

  • C FrontierAgent Yet another agent framework: TUI, ReAct, Agent Team modes, one-command install. The feature list isn't short, but it doesn't say what new problem it solves compared with mature frameworks like LangGraph or OpenHands; the description is mostly marketing, and 14 stars in two days isn't evidence either. #AI Agents#LLMs#CLI

    🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.

    ApodexAIPython★14

  • C slider-captcha-lab Packages slider, jigsaw and click-based CAPTCHA recognition, trajectory modeling and server-side validation into an experiment bench. The tech isn't crude, but its sole purpose points to bypassing human verification, it has a short lifespan, and it's unsuitable as a learning example. #Crack#Automation#Images

    Recognition algorithms + behavioral trajectory modeling + server-side validation replication for four types of graphical CAPTCHAs—slider / jigsaw / restoration / click-select—plus a Vue console that l…

    a1952304267Python★13

  • C agent-book Yet another "Enterprise Agent from Beginner to Expert" tutorial; the accompanying end-to-end project and CI gates show some sincerity, but it's essentially tutorial notes, and reading the docs beats reading the repo. #AI Agents#Learning#LLMs

    "Enterprise Agent from Beginner to Expert (2026 Edition)" — an engineering-oriented hands-on tutorial from single-Agent core mechanisms to multi-Agent and enterprise deployment, with a runnable end-to…

    cdavid817Python★8

  • C agent-dev-workflow "A hand-rolled coding agent with a recoverable dev workflow" reads more like personal workflow notes, with no code, install method, or verifiable results. There are already many similar agent workflow articles. #AI Agents#LLMs#Automation

    A practical, resumable development workflow I hand-built for AI coding agents.

    hoperswzLanguage unknown★11

  • C claude-code-cheat-sheet Yet another Claude Code cheat sheet, a pure content repo whose value rests entirely on the author's personal experience—unverifiable and not reusable as a tool. Official docs and community notes already cover this, so it isn't worth ten minutes. #LLMs#Learning#CLI

    A practical Claude Code cheat sheet from first command to power-user workflows.

    musichenLanguage unknown★11

  • C antigravity_chinese_v2 A Chinese localization patch for Google Antigravity, implemented by replacing resources. The audience is narrow, it breaks whenever upstream updates, and installation and rollback aren't documented—a personal tinkering product; users wanting a Chinese UI are better off changing the official language setting. #Editors#Plugins#antigravity

    Anti-gravity Chinese localization

    nianshou555qiansuiPython★10

  • C monster-avatar A fun web tool of the little-monster avatar generator kind. The description is one sentence, with no word on how it generates, whether it exports, or what it depends on; similar avatar generators are everywhere, so there's no must-see reason. #Image Generation#Web Frontend#Images

    Little Monster Avatar Generator

    ns2250225TypeScript★7

  • C nova-trade-ai Yet another AI stock-picking platform: CANSLIM analysis plus DeepSeek chat, one-click Docker deploy. The feature list is full, but there's no method validation or backtest evidence; it's essentially an LLM wired to a market data API, and similar projects have been plentiful this year. #LLMs#Fintech#Data Analysis#docker

    An open-source AI-powered stock research platform featuring CANSLIM analysis, real-time financial data, DeepSeek chat, and one-click Docker deployment. Chinese intro: open-source AI intelligent invest…

    wangchenxi99Java★12

  • C edgeprovisioning A server initialization script meant to install the infrastructure needed for deployment on a new machine; bootstrap scripts like this are everywhere, and the description only says "essential infrastructure" without stating what it installs or which distros it supports. Eight stars in two days with no usage signs, so no reason to open it for now. #DevOps#Linux#Automation

    A simple toolkit for provisioning fresh servers and setting up the essential infrastructure needed to deploy and run applications.

    0x66616C6C656EShell★8

  • C sprawling Claims to be a local multi-agent city for long-running agent teams and social simulation, a classic vision-first project: it doesn't explain how any concrete scenario runs or what resources are needed. Gaining 24 stars in a day or so looks more like riding the agent hype than real usage. #AI Agents#LLMs#Self-Hosted

    Local multi-agent city for running persistent agent teams, long-run, society-simulation

    2youg1Rust★24

  • C wp-plugin-ai-hardening Generates a set of prompts for security-auditing AI-written WordPress plugins. The problem is well chosen, since AI-generated plugins do tend to miss escaping and capability checks, but the deliverable is only prompts, with no check scripts or rule sets, so results depend on the user. #App Security#Prompting#Plugins

    Generate structured security audit prompts for WordPress plugins created with AI, based on official WordPress security guidelines.

    Webhosting4UHTML★7

  • C herdr-plugins A set of Nix plugins for the Herdr terminal workflow, aimed only at people already using Herdr, and the repo doesn't explain what each plugin does, so outside readers can't judge its value. #Terminal#Plugins#Linux

    Focused plugins for Herdr terminal workflows.

    choplinNix★9

  • C openAVO Aims to unify prediction, memory, supervision, and verification for long-horizon autonomous agents on ARC-style interactive tasks. The vision is large and the jargon dense, but there are no runnable usage or result examples—a typical empty platform; wait for a demo. #AI Agents#LLMs#ML Research

    OpenAVO is an open harness for long horizon autonomous reasoning, combining prediction, memory, supervision, verification, and adaptive action loops to improve agent reliability on ARC AGI style inter…

    ruvnetLanguage unknown★7

  • C dsh-everything Evolves Agent Harness into a protocol plus examples where everything is a plugin, piling up jargon without a runnable entry point; similar agent orchestration schemes already abound, and it doesn't clarify which specific problem it solves for you. #AI Agents#Agent Skills#Plugins

    A coding-agent protocol and examples for evolving Agent Harnesses into Everything Is Plugin architectures.

    yshenawPython★7

  • C evidence-first-problem-solving The same author published multiple Agent Skill repos within 24 hours with highly similar descriptions, making it hard to tell which is actually used. The skills are text workflows with no examples or evaluation, so they're not worth the time. #AI Agents#Agent Skills#Prompting

    An open Agent Skill for evidence-first investigation, decisive execution, and proof-backed completion in Codex and Claude Code.

    aiopshwangPython★8

  • C goal-to-proof One of a batch of mass-produced skills, claiming agents should complete authorized work and prove it with evidence, which sounds right but has no runnable implementation or real cases. It's indistinguishable from the author's other four repos. #AI Agents#Agent Skills#Prompting

    Make AI agents finish authorized, non-trivial work and prove the requested outcome with direct, scope-matched evidence.

    aiopshwangPython★9

  • C douyin-keeper A dual-channel script that automatically renews Douyin friend streaks, a small automation tool against the platform that could be killed by risk controls at any time, and it doesn't solve a new problem. #Automation#Social#Productivity

    Douyin streak renewal assistant - dual-channel automatic streak renewal tool

    diyiqiuyePython★9

  • C returnline A macOS workbench that saves task context and helps you return to the original task after drifting. The concept is appealing, but the description stops at vision, without saying how context is captured or which apps it integrates with. #macOS#Productivity#Knowledge Base

    Returnline — a local macOS workbench that helps save task context and re-enter the original task after drifting away.

    mollyhan-aiJavaScript★6

  • C Loyal-Bear---The-SynthID-Scrambler Automatically erases SynthID watermarks from images, effectively stripping the provenance marker from AI-generated content. Technically it's just perturbation targeting one watermark, useful to people who want to hide generation traces, but legitimate uses are limited, and it doesn't address effects on other watermarks or metadata. #Watermarks#Images#AI

    Automatically remove SynthID from any image

    BovineOverlordPython★7

  • C v2plus An Android proxy client based on v2rayNG and Xray-core that calls itself "faster and more stable," but is essentially another fork. For ordinary users, upstream v2rayNG is still maintained, so unless it clearly states which specific problems it fixes, there's no reason to switch. #Networking#Android#Privacy

    Быстрый и надежный прокси-клиент для Android на базе v2rayNG и Xray-core.

    GoodbyeWLKotlin★6

  • C HaizhuRemakefaceWebui A web workbench for face redrawing, part of the Haizhu series. Tools like this have a low technical barrier but high abuse risk, and the repo doesn't state model sources, licensing, or usage restrictions; 13 stars just 0.1 days after creation makes actual results even harder to judge. #Image Generation#AI#Web Frontend

    remakeface WebUI — face redrawing web workbench (Haizhu series)

    HaizhuAIPython★13

  • C shifu Claims to give AI coding agents "adaptive process depth," but the one-liner offers no verifiable mechanism: is it a prompt layer, a scheduler, or a hook? 20 stars in a day shows the name works, but readers can't tell if it actually improves coding workflows. #AI Agents#LLMs#CLI

    SHIFU (师父) — adaptive process depth for AI coding agents.

    LongadoShell★20

  • C DanmakuFuzz The name and description are just one line, 'let's fuzz Gensokyo,' leaving unclear whether it fuzzes bullet-hell games or something else. Fun but uninformative: it can't be installed and there's no way to judge what it might find. #Testing#Games#Debugging

    Let's fuzz Gensokyo :)

    Touhou-LabPython★11

  • C ship-mobile-app Claims one skill covers the entire mobile delivery chain across Flutter, RN, iOS and Android, and such 'does everything' descriptions are the hardest to verify. With no sample output, skip it for now. #AI Agents#Agent Skills#iOS#Android

    An open Agent Skill for Claude Code and Codex to build, debug, and prepare production mobile apps across domain, state, lifecycle, native platform, signed artifact, and user-claim boundaries. Framewor…

    aiopshwangLanguage unknown★8

  • C outlook-auto-register A tool for bulk-registering Outlook accounts via pure protocol, technically somewhat interesting. But its use is basically mass account farming, part of a grey-market toolchain, so it isn't recommended. #Automation#Scams#APIs

    Microsoft Outlook Fluent Web API protocol registration tool (pure protocol, no browser dependency)

    lxf746Python★9

  • C home-assistant-keypad From the name, a small keypad entity for Home Assistant, possibly a hardware project. But it says nothing about what hardware, how to wire it, or how to connect it to HA—a half-finished placeholder. #IoT#Hardware#Self-Hosted

    realworldpixelLanguage unknown★21

  • C wisdomforge-kids-Hermes-profiles A Hermes parental-managed configuration for children, tiered by age, explicitly stating it is not a children's AI product. The scope is narrow, but it doesn't say what the configuration actually restricts, making it hard for outsiders to assess—more like a public copy of internal material. #LLMs#Privacy#AI Agents

    Parent-operated Hermes profiles for children in WisdomForge bands 5–10, 11–14, and 15–18. Fresh profiles only. Not a kids-AI product.

    smfworksPython★7

  • C Make_Mentors_Great_Again A Codex skill that turns an advisor's materials into a research knowledge base and automatically finds Research Gaps, with a punny name and grand goals; a 'defensible gap' is hard to produce via prompts, and while it tempts grad students, it still looks like prompt wrapping. #Agent Skills#Knowledge Base#Science#AI Agents

    A discipline-neutral Codex skill that turns mentor-shared sources into a research knowledge base and defensible Research GAPs.

    zxc-CCCLanguage unknown★6

DSkip122
  • D gpt2.cmake Implements GPT-2 purely in CMake, showing technical cleverness but with very low practical use; 44 stars are driven by technical appreciation rather than real demand. Commercialization is impossible since inference efficiency is far below standard frameworks, competing with PyTorch and TensorFlow as a technical curiosity. #ML Research#LLMs#Build#gpt-2

    Implementation of the GPT-2 model in pure CMake

    AlpinDaleCMake★44

  • D douban-movie-assistant Detects and plays video sources directly in a Douban sidebar for convenient binge-watching; 30 stars show demand, but it involves copyright and platform rules with high commercialization risk. Competitors are various video aggregation plugins, and sources need timely updates. #Browser Extensions#Streaming#Video#Productivity

    Watch directly from the sidebar on Douban movie/series pages: four-channel detection of playable sources, inline muted preview within cards, episode selection, and follow-up update reminders

    alchaincyfJavaScript★30

  • D grok-bot-0.18-reconstructed An unofficial rebuild of Grok Bot 0.18 for specific macOS versions, addressing personal use but with a very small user base; 159 stars come from a specific community rather than an incremental market. There is no commercial potential and possible copyright infringement, competing with the official version. #AI#LLMs#macOS#Reverse Engineering

    Unofficial source-oriented reconstruction and extension of Grok Bot 0.18.0 for macOS

    b-nnettTypeScript★159

  • D chatgpt-markdown-latex-copier Copies ChatGPT-rendered LaTeX as Markdown, addressing researchers' copy formatting issues; 33 stars is few but demand is real. Commercialization is difficult since browser extensions are hard to charge for, competing with native browser copy, but it could integrate into knowledge management tools. #Browser Extensions#LLMs#Productivity#Documents

    Copy ChatGPT web responses containing LaTeX formulas as well-formatted Markdown.

    hxhou0207JavaScript★33

  • D kumone-ios16 A compatibility version for iOS 16 addressing missing features in specific jailbreak environments; 45 stars come from a specific user group with no broad demand. There is no commercialization path and the jailbreak ecosystem is shrinking, competing with official app store alternatives. #iOS#Jailbreak

    An iOS 16-compatible version of Kumone, verified on a real iPhone 13 / iOS 16.0 / TrollStore device

    lcmovieSwift★45

  • D seed An interactive 3D seed explorer generated with threejs and Claude. It solves no real need and is purely a demo; its 34 stars come from visual appeal but it lacks practical value, has no commercialization potential, and competes with the many threejs demos. #3D#AI#Web Frontend

    An interactive 3D seed explorer built using threejs with Claude Opus 5

    thebuggeddevTypeScript★34

  • D plack One line, "a quick switcher for impatient people," a small macOS tool written in Swift, but it doesn't say whether it switches apps, windows, or files. macOS launchers already have strong incumbents like Raycast and Alfred, and there's no differentiation explained. #macOS#Productivity#CLI

    quick switcher for quick people

    DakshG07Swift★10

  • D HA-Home-Remote A remote-control interface for Home Assistant, used with ESPHome; the description is one sentence and says neither which parts of the official app it replaces nor how to install it. Self-hosted remote-control options already exist, and it lacks differentiators. #IoT#Self-Hosted#Automation

    Home Remote for Home Assistant that uses esphome

    GeckoZALanguage unknown★7

  • D Evaan_Personal_Intelligence_Engine A fully local companion chatbot using Qwen2.5-0.5B with a persona and JSON-persisted memory, usable offline once installed. The positioning is honest, but local small-model chat projects are plentiful and it offers no differentiation, so its value rests entirely on how well the persona prompt is written. #LLMs#AI Agents#Privacy

    Evaan — a fully local, offline-capable AI companion chatbot built with Python & Hugging Face Transformers, running on Qwen2.5-0.5B-Instruct (CPU-only, no fine-tuning). Features a persona-driven system…

    Tahirpathan-AiLabPython★10

  • D SkyStar-AI An emoji-heavy "Pakistan AI assistant" desktop app bundling voice, chat, weather, news, and image editing, exactly the kind of do-everything project to be suspicious of. There's no credible technical explanation and no sign it beats existing assistants. #Speech#Images#LLMs

    🌟 SkyStar AI - Pakistani AI Assistant by Sahil Ahmad - Voice, Chat, Weather, News, Image Editor - Professional Desktop App

    bahmad-blipLanguage unknown★9

  • D dsh-markdown Claims to be a lightweight 'smart' Markdown editor but doesn't say where the smarts are or how it differs from Typora and Obsidian; one line of description and a dozen stars suggest it's more a personal editor open-sourced on the side. #Editors#Documents#Productivity

    A lightweight intelligent Markdown editor

    yueyezhufengTypeScript★10

  • D deepseek-whalechan Claims it can keep a character consistent across generations, but delivers setting docs, an asset library, and an agent, more like a fan project than a tool. It doesn't explain how to plug into existing art workflows, and consistency can't be verified. #AI#Image Generation#Prompting

    Keep Whale-chan consistently vivid in every generation: High-consistency character design specification, visual asset library, and agent creation suite.

    Neko3000Python★14

  • D siep A school project e-commerce system built with PHP, MySQL, and MVC plus PDF reports; the feature list is long but stays within coursework scope. Anyone looking for a ready-made e-commerce solution won't benefit here. #E-commerce#Learning#Databases

    SIEP | Sistema de Información E-commerce para Papelería ISA&CRIS | PHP + MySQL | Arquitectura MVC | CRUD Completo | Reportes PDF (TCPDF) y Excel | jQuery + Ajax | Bootstrap | Metodología XP.

    andrea-lopez-devCSS★7

  • D rosterroom 82 team configuration texts you can paste directly into Grok Bot, a content collection rather than a tool that anyone else could write differently. It saves Grok Bot players some effort but lacks engineering value. #Prompting#LLMs#Content Writing

    82 original, guarded team rosters ready to paste into Grok Bot.

    codejunkie99Language unknown★12

  • D Korean-llm-v3 A PyTorch implementation of Korean LLM training built for learning purposes. Its 28 stars show educational value but no unique innovation, and commercialization is hard given the many open-source Korean models; it competes with Polyglot and Korean-LLM and needs to show training results. #LLMs#ML Research#Learning

    PyTorch-based Korean LLM implementation and training project

    seoan1024Python★28

  • D MileHost-MCP An MCP server for AI dev environments like Claude Code, whose description stresses "just let the agent download this MCP itself," but never says when you'd need it or which tools it provides. MCP servers are proliferating, and without a concrete use case there's no reason to pay attention. #MCP#AI Agents#Self-Hosted

    mcp сервер для Claude Code/Antigravity и др. сред разработки с ии агентами. Простой в использовании: просто попроси своего агента скачать данный mcp

    Mile-HostJavaScript★6

  • D Smart-India-Hackathon-SIH-2026-Problem-Statements A pure-data repo collecting hackathon problems as CSV/JSON/MD, mildly useful for students browsing challenges, but with no tools or methods it's a one-off copy of what the official site already has. More worth bookmarking than using. #Learning#Documents#Data Analysis

    All Smart India Hackathon (SIH) 2026 Problem Statements in CSV/JSON/MD formats.

    NoBugNinjaLanguage unknown★7

  • D shanframe Its slogan is "your machine, available to you and your agent anytime," with an agent and CLI, but it never explains remote access, authentication, or NAT traversal. Vision outpaces usage, and mature options like tailscale and frp already cover the same need. #AI Agents#CLI#DevOps#Self-Hosted

    Your machines, from anywhere — for you and your agents. The shanframe agent + CLI.

    ShawnPanaGo★12

  • D demo-linkedin-agent A Fetch.ai example of a LinkedIn posting agent that the author labels a demo. Beginners learning uAgents and Agentverse can copy it, but example code decays fast, and it gathered twenty-plus stars within hours, looking more like circle promotion. #AI Agents#Social#LLMs

    Fetch.ai LinkedIn poster agent for Agentverse using uAgents and ASI:One

    ShyamRVPython★28

  • D e621 A community-maintained project based on e621 open-source code for an adult content community, addressing self-hosting needs for a narrow audience; 80 stars come from a niche circle with no mainstream commercial value and high legal risk. Competitors are official platforms, and the technical barrier is low. #Adult Content#Images#Databases

    An independent community-maintained project based on the open-source "e621" codebase.

    blendmaidintrigueRuby★80

  • D md.html A Rust repository with no description; the name suggests Markdown to HTML. Such tools are already saturated, and without an explanation there's no reason to try it. #Documents#CLI#Web Frontend

    feliperunRust★8

  • D RelayPilot From the name, a Swift desktop tool for managing relay endpoints for Codex and Claude. There's no description and no word on supported protocols or configuration, so a freshly created repo can't support a credible judgment. #LLMs#macOS#APIs

    Desktop relay manager for Codex and Claude

    start-zaneSwift★9

  • D windows-mac-single-brain Describes a "single brain" architecture that bridges Hermes on Windows to a Mac over SSH, more a personal configuration record than a reusable install script or design writeup. Anyone following it would have to fill in a lot of details themselves. #AI Agents#macOS#Windows

    Hermes Agent single-brain architecture: one Hermes on Windows controlling Mac + Windows (SSH bridge, Dashboard tunnel, terminal alias)

    Jack0813yLanguage unknown★10

  • D NeoWorker Self-described local-first 'AI work operating system' covering research, writing, coding and automation, with GUI, CLI, Skills and MCP. Trying to do everything means it never says which problem it solves first, and such all-encompassing projects usually fail to land. #AI Agents#LLMs#MCP#Productivity

    Open-source, local-first AI work operating system for research, writing, coding, automation, and deliverable creation—with GUI, CLI, Skills, and MCP support.

    Yuan-lab-LLMTypeScript★14

  • D nature-story A "narrative architecture" aimed at engineering and human settlement research, essentially a research writing methodology rather than a runnable tool. There's no code to try, so developers can't use it. #Science#Content Writing#Learning

    Evidence-grounded scientific story architecture for engineering and coupled human-environment research

    haohuresearchLanguage unknown★7

  • D solid-gpui A repo with no description; the name suggests wiring Solid's reactive model onto Rust's GPUI, but no documentation confirms this or explains how to use it. #UI Design#Web Frontend#SDKs

    lxsmnsycRust★10

  • D deepseek-harness-hello-kitty-suite A pink Hello Kitty skin plus task-completion reminder plugin for DeepSeek Harness, full of emoji, purely decorative. A little toy for people who like this aesthetic, but it solves no engineering problem, and similar theme plugins have already appeared in batches in this ecosystem. #Plugins#UI Design#AI

    💗 A pink Hello Kitty theme skin for DeepSeek Harness + task-completion/question notification plugin (Sweetheart Workspace Expressive skin & Hello Kitty Task-Done Notifier)

    Angel2518975237JavaScript★9

  • D FDUEGA_RM2026_Waves_Analyze Information-wave parsing code for Fudan EGA team's RoboMaster radar station, one link in the team's internal toolchain. It has reference value for competing teams, but lacks data-format documentation and run instructions, so outsiders can barely reuse it. #Robotics#Data Analysis#Learning

    RoboMaster 26 season Fudan University Nebula EGA team radar parsing information wave repository

    Breeze-byMATLAB★9

  • D aws-dva-c02-notes AWS certification study notes where the author openly flags that most content is AI-generated and official docs should be trusted instead; that honesty deserves credit. But it's still personal review material, neither a tool nor a structural innovation, fine for a quick skim. #Learning#Documents#Knowledge Base

    Study notes for AWS DVA C02 cert. Most contents are AI-generated, please check against the current official AWS docs as final facts.

    P311Language unknown★9

  • D Frame-Patcher No description; the name hints at frame processing but it's unclear whether for games, video or emulators. Nineteen stars in one day with no readable information means usability can't be assessed. #Performance#Games#Debugging

    aimolodcaPython★19

  • D genpark-agentic-qe-full-stack-test-plan-executor-skill Both name and description look like an auto-generated 'platform' template, bearing the TestMu AI name but showing no implementation. The more of these skill-farm repos appear, the more wary one should be. #AI Agents#Agent Skills#Testing

    Agentic QE platform automating full-stack test plan creation, execution and release gate decisions (TestMu AI style)

    alphaparkincPython★8

  • D zerorecon A reconnaissance repository with no description; the name points to information gathering but says nothing about targets, usage, or legal boundaries. Security tools without documentation especially should not be recommended. #Network Security#App Security#CLI

    devx07-techPython★6

  • D PSX3IOS Claims to be an iOS PS3 emulator based on RPCS3, but iOS lacks JIT, the repo was created in a day and a half, and it doesn't even list a language, so it almost certainly can't run yet; appealing to those wanting PS3 games on iPhone, it currently looks like an empty shell riding emulator hype. #Game Porting#Games#iOS

    A PlayStation 3 emulator for iPhone and iPad, built on RPCS3. Beta.

    xmiguel911xLanguage unknown★13

  • D doompi The title calls itself a "PI agent harness distribution," but the README doesn't say whether it's a distribution, a mirror, or a config collection, so readers can't tell what installing it gets them. Harness-adjacent projects like this have appeared in bulk recently, and it lacks any verifiable differentiator. #AI Agents#LLMs#CLI

    PI agent harness distribution

    AgiFlowTypeScript★17

  • D community-plugins A community plugin list for the Hermes desktop client that only collects entries without auditing them. It's content aggregation rather than a tool, and its value depends on whether the upstream ecosystem really exists; list repos are heavily homogenized, and readers can't tell which plugins actually work. #Plugins#Knowledge Base#Productivity

    Curated list of community-made plugins for the Hermes desktop client. Listed, not audited.

    AtlasOmniaLanguage unknown★16

  • D codex-app-server-gateway-guide A practical tutorial on wiring Codex App Server into an existing chat frontend and gateway, covering streaming events, thread lifecycle, and MCP tool sync. Useful for engineers doing similar integrations, but it's tutorial notes that will age quickly as upstream APIs change. #Learning#APIs#MCP

    A practical tutorial on integrating Codex App Server into existing chat frontends and gateways, covering streaming events, thread lifecycle, refill, multi-backend routing, and MCP tool synchronization…

    KKarsylineLanguage unknown★11

  • D Belanja-Kuota-QRIS Undescribed; judging by the name, it's a small local app for buying Indonesian phone credit and data packages with QRIS payment, likely a personal exercise or small-shop tool. With no documentation, it can't be evaluated or recommended to anyone. #Fintech#E-commerce#Web Frontend

    alimron16JavaScript★7

  • D genpark-database-query-plan-index-tuning-engine-skill Aims at execution plan analysis and index tuning, but has no examples or evaluation, only a one-line description benchmarking pganalyze. For real tuning, mature tools and Postgres's own statistics are already sufficient. #AI Agents#Agent Skills#Databases

    Autonomous database query plan analyzer and index tuning engine detecting sequential scans (pganalyze style)

    alphaparkincPython★8

  • D ComfyUI-Magicframe A ComfyUI node extension with no description; the name only hints at frame or image processing. The ComfyUI ecosystem has many plugins, and without an explanation there's no reason to install it. #Image Generation#Plugins#Images

    chyueyiPython★7

  • D finops-ia A FinOps-related repository written in HCL with zero description, so it's unclear whether it's a Terraform module or a cost reporting solution. Without an explanation there's no entry point for evaluation. #DevOps#Automation#Data Analysis

    douglsHCL★14

  • D omni.nvim Yet another Neovim color scheme, with seven variants and a "your last color scheme" tagline, but no explanation of differences beyond screenshots. This space is already severely oversaturated. #Editors#Plugins#UI Design

    The last Neovim colorscheme you'll ever need. 7 carefully crafted flavours, one unified theme.

    harshrajsachanLua★11

  • D shoal A fish school animation following the mouse, purely visual with no practical use; 27 stars come from entertainment and design appreciation but offer no productivity. There is no commercialization, competing with the many creative coding snippets. #Animation#Web Frontend#UI Design

    School of fish that reacts to cursor movement

    rishabdesignsJavaScript★27

  • D agents-fleet Calls itself the "blank but usable source of truth" for Claude Code and Codex on macOS/Linux, phrasing so abstract that you can't tell whether it provides config templates, syncing, or a launcher. Concept-first, missing the first step anyone could follow. #AI Agents#LLMs#CLI

    A blank, working source of truth for Claude Code and Codex across macOS and Linux.

    Bil0000Python★11

  • D dsh-preset-plus A preset-editing plugin for DSH whose headline is "one-click jailbreak," i.e. bypassing model content restrictions. Such tools live only until the platform blocks them, offer no technical accumulation worth discussing, and don't qualify as a noteworthy development project. #Jailbreak#Prompting#Plugins

    DSH preset editor plugin, supports one-click jailbreak.

    Rain-klJavaScript★12

  • D genpark-lidar-d-shape-autonomous-floor-mapping-robot-skill This compresses a laser SLAM robot vacuum into a skill description with no algorithms, data, or runnable code. Even robotics people get nothing usable from it. #AI Agents#Agent Skills#Robotics

    Laser LiDAR SLAM floor mapping and D-shape robotic vacuum cleaner (Neato style)

    alphaparkincPython★8

  • D home-assistant-alarm-manager No description; from the name it's a Home Assistant alarm panel management add-on. With no docs on configuration or supported versions, it can't be installed or evaluated. #IoT#Self-Hosted#Automation

    cybersquatbisPython★6

  • D how-to-fish-utility An enhancement tool for the specific fishing game How to Fish, similar to a cheat, modifying game data for convenience; 102 stars in 1.6 days come from the game community, growing fast but with a narrow audience. Commercialization is hopeless with legal risk, the strongest competitors are various game modifiers, and utility is low. #Game Cheats#Games#Scams

    Enhancement tool for How to Fish — unlock the full potential of your fishing adventure

    kevin-v-eng97e2Python★102

  • D Comment-Project A community comment system written in Go/Kratos that the author describes as a learning project. It covers BFF, moderation, search, and caching, quite complete as practice, but it has no use for others and is essentially a personal assignment. #Learning#APIs#Databases

    Go/Kratos learning community comment system | BFF, moderation, search, cache, async counters

    weiyi-chGo★12

  • D qualification-test It tests eligibility for an OpenAI account 'gcash pay', suspected to be a gray-market tool. It addresses regional payment restrictions but violates platform terms; its 35 stars come from irregular demand, there is no legitimate commercialization, it competes with virtual card services, and the risk is extremely high. #Scams#Fintech#APIs

    Test your openai account gcash pay qualification

    yeying-xingchenPython★35

  • D AMDL An Apple Music downloader for Android that directly grabs paid streaming content, making it a piracy tool. Technically unremarkable, with legal and account risks borne by users; not a noteworthy open-source project. #Piracy#Downloaders#Android

    Apple Music Downloader for Android

    Kyant0Kotlin★11

  • D open-omada-device-agent The README leaves no explanation, so one can only guess from the repo name that it relates to a TP-Link Omada device proxy. With no visible use case or deployment instructions, it offers readers zero information, so it's not recommended for now. #Networking#DevOps#Monitoring

    adryanalencarPython★6

  • D genpark-b2b-dealership-used-car-auction-remarketing-skill From the same batch of generated skill repos, compressing a used-car auction platform into a single sentence with no code, data or runnable parts. Beyond the name there is almost nothing to evaluate. #AI Agents#Agent Skills#E-commerce

    B2B dealership used car remarketing auction platform (CarOnSale style)

    alphaparkincPython★8

  • D Bertani A Lua repository with zero description, so it's impossible to tell whether it's a game mod, script, or something else. It got 8 stars in a day but offers no readable information, so clicking in just wastes time. #Games#Game Dev#Plugins

    amnottdevvLua★8

  • D CA-Firm-Automation-Suite Claims to be a JSON workflow automation suite for accounting firms, but beyond that sentence there's nothing, and the scenario isn't explained. Impossible to tell whether it's a tool or a template pack. #Automation#Documents

    Full JSON workflow for CA Firm Automation Suite

    tanlovepainLanguage unknown★8

  • D awesome-thai-ai-projects Another awesome list, this time products built with AI by Thai developers, also organized into JSON, showing some curation effort. But it offers readers no actionable next step. #AI#Learning#Data Analysis

    A curated list of 200+ real products, apps, bots, and tools that Thai developers built with AI — Claude, Codex, Gemini and friends. Extracted, PDPA-sanitized, and categorized from community threads in…

    iaunnPython★9

  • D telehack The author is well known, but the repository has no description, so it's impossible to tell whether it's a terminal toy or a network protocol experiment. Fame brings attention, not usability; wait for documentation. #Terminal#Networking

    shi3zPython★6

  • D Starhub-Tutorials A Chinese PDF tutorial on basic architecture and implementation, delivered as a static document that neither runs nor ships companion code. Unless you happen to be studying this architecture, there's no reason to open it, and its accuracy can't be verified. #Learning#Knowledge Base#Documents

    StarHub infrastructure and implementation tutorial (PDF)

    StarhubQiaoLanguage unknown★13

  • D OCTANE A JavaScript repository with no description; neither the name nor the contents give any clue for judgment, so it can only be treated as unknown. #Automation#Web Frontend#Productivity

    bigboi-altJavaScript★7

  • D aleph-hackathon A hackathon entry whose description is just one line, "AI Solution for Aleph Hackathon 2026," saying neither what problem it solves nor how, so it can't be evaluated. #AI#Learning#Collaboration

    AI Solution for Aleph Hackathon 2026

    felipebridgePython★7

  • D PixelStrike No README description, implemented in TypeScript, named PixelStrike. Can't tell if it's a game, an image tool, or a frontend experiment, and 12 stars in a day proves nothing. #Games#Web Frontend#Learning

    MineSunshineoneTypeScript★12

  • D AI-Infra No description, and the subject appears to be the D2 diagram language, guessed to be architecture diagrams or similar; the purpose can't be determined. #DevOps#AI#Self-Hosted

    cdavid817D2★7

  • D selfdb The README is empty and the repo name doesn't explain what it does; getting 72 stars in half a day looks more like star farming than real demand, so it can't be evaluated. #Databases#Self-Hosted#Privacy

    fzakariaPython★72

  • D treeboat-weread-style No description; the repo name suggests a WeChat Reading-style theme recreation, but there's no finished-product explanation, screenshots, or usage, so it can't be evaluated. #UI Design#Web Frontend#Documents

    lulululillianPython★17

  • D vincio Claims to be a real-time collaborative workspace with terminal execution and local AI, three big things in one sentence, a classic repo that wants to do everything and shows nothing. With no verifiable capability boundaries, it's not worth the time. #Collaboration#Terminal#AI

    "Real-time collaborative workspace, terminal execution, and local AI integration."

    vinyassystemsHTML★6

  • D hermes-profile-packs A collection of configuration profiles for Hermes Agent, i.e. content aggregation; it doesn't say what scenario each profile solves or which model it depends on. It might save beginners some effort, but lists like this tend to go stale quickly. #AI Agents#Prompting#Productivity

    Curated Hermes Agent profile packs

    Dadmin88Python★6

  • D options-pricing-tool No README description; the name suggests an options pricing calculator in Python. The pricing model, supported underlyings, and output format are all unspecified; Black-Scholes calculators are readily available, so there's no evaluable increment. #Fintech#Data Analysis#Learning

    Hakman21Python★7

  • D grok-bot-orange-book A Chinese "orange book" around Grok Bot covering multi-agent collaboration, Routines, and automation cost savings. It's a tutorial and content repo whose methods will break fast as the platform changes, and its numbers are hard to verify. #Prompting#LLMs#AI Agents

    Grok Bot Orange Book "Put an AI Team in Your Pocket": from beginner to advanced · multi-agent collaboration · Routine · saving money and automation

    KinGao294Language unknown★26

  • D bot-making-resources A collection of character bot prompts and tutorials for JanitorAI and SillyTavern, a content repo with no tool to evaluate, so it isn't recommended under the rules. #Prompting#LLMs#Learning

    A bot making resources dump. Including guides from other creators and my personal's guide. Mainly for JanitorAI and Silly Tavern.

    iamKETLanguage unknown★6

  • D GOLLM A Go repo with no README explaining what it does; 27 stars within two days looks more like traffic from the name than real usage. #LLMs#AI#APIs

    lshan02508-aiGo★27

  • D listing-toggles An undocumented Python repository with no description; the name doesn't reveal which list it toggles, and there's no way to judge whether it works. Not worth a look. #E-commerce#Automation#UI Design

    milankovoPython★16

  • D media-downloader The repository has no description; the name suggests a media downloader. There's no way to tell which sites it supports, whether it's compliant, or how to start, so as it stands it isn't worth opening. #Downloaders#Video

    pxniicPython★8

  • D TinyVLA No README description; the name suggests a small vision-language-action model implementation. VLA reproduction is hard, and without weights, data, or training notes it's basically unusable until the author fills those in. #ML Research#Robotics#AI

    Lin-zttPython★6

  • D Smart_Study_Monitor An undescribed 'study supervision' utility that, judging by its name, is a student assignment or personal project, with no explanation of what it monitors, how to use it, or which platform it runs on. Such repos usually go quiet within days, so it can't be recommended. #Learning#Productivity

    SwastikBiswas26Python★11

  • D Kraken-DCA-Auto-Trading-Bot The description is just a marketing-style name with a year, with no strategy, risk control, or operation instructions, a typical crypto trading bot template. Such repos often come with star farming and aren't worth the time. #Crypto#Fintech#Scams

    KrakenBot — Kraken Auto Trader 2026

    gargantuangrLanguage unknown★20

  • D gh900-handout Japanese lecture materials for GitHub Foundations (GH-900) training, which is course material rather than a tool, so it isn't recommended. #Learning#Documents#Knowledge Base

    Handout materials for GH-900 GitHub Foundations attendees (Japanese exercise instructions)

    mamezouLanguage unknown★11

  • D Copilot-Bridge- A repo with no description whose name suggests a bridge for Copilot. It's unclear what it bridges or how to start using it, so by the rules it doesn't count. #LLMs#APIs

    vipamessGo★6

  • D marzban-node The name directly reuses Marzban's node component, with no description and only a Dockerfile, looking like a mirror or name-squat of a proxy panel. No new content is visible. #Networking#Self-Hosted#marzban

    x4gpanellDockerfile★13

  • D intelligent-alert-monitoring-using-aiops Beyond restating the repo name there's no explanation, so it's unclear whether this is alert noise reduction or yet another AIOps platform; audience, data sources, and startup steps are all missing, a typical practice project. #Monitoring#Observability#AI

    intelligent-alert-monitoring-using-aiops

    yudaysurendra-gifPython★9

  • D braxis-blueprint A script collection under the "$0 AI empire" banner: 140+ agents, 20+ free LLM channels, 1800 songs, all marketing numbers. It's a content collection rather than a runnable project, with failure lessons mixed into promotional copy and nothing verifiable. #AI Agents#LLMs#Prompting

    The $0 AI Empire Playbook — 140+ agents, 20+ free LLM lanes, 1,800+ songs, a living 3D world, all on free tiers. Real scripts, real failure classes, MIT.

    BraxisAIPython★34

  • D Base-Chain-Memecoin-Sniper A memecoin sniping bot for the Base chain with an empty README. It offers neither strategy explanation nor risk warnings, and tools like this are also a high-incidence zone for getting counter-sniped and rug-pulled, so there's no evaluable engineering value. #Crypto#Blockchain#Automation

    CheetahAwakenC#★9

  • D KarhuAC An anti-cheat project whose README only says "public source release," with no word on which games it covers, what behaviors it detects, or how to integrate. Anti-cheat work needs credibility and integration docs, and neither is here; 17 stars prove little. #Anti-Cheat#Games#Network Security

    Public source release

    Karhu-AnticheatJava★17

  • D Kof-Editor No README description; named Kof editor and implemented in Java. There's no way to tell whether it's a text editor, a game modding tool, or something else, leaving readers with nothing to go on. #Editors#Productivity#CLI

    KofLangJava★15

  • D deepagents-learn The author's own deep learning notes, with no reusable tools or frameworks, and others can't run them anyway. It's personal practice notes with no reading value unless you happen to be following the same tutorial. #Learning#AI Agents#LLMs

    Deep Agent learning records repository

    Pjk-llmPython★6

  • D jiofarm An empty README, and neither the repo name nor language reveals its purpose, yet it has 53 stars within hours of creation. There is nothing to evaluate. #Science#Data Analysis#Automation

    hirotomasatoPython★53

  • D Webopsy An empty README, and neither the repo name nor description explains what it does, yet it has 16 stars on its creation day. There is nothing to evaluate. #Web Frontend#Data Analysis#Automation

    kajalpandey0101Python★16

  • D Cat The repo has only a name, no README description, and a Python implementation, so its function and purpose can't be determined. No usable information for readers. #Learning#Productivity#CLI

    EkibenyaPython★16

  • D Portfolio A personal portfolio site that nobody but the author will use. The code might serve as a one-time frontend exercise, but it has no reusable components or ideas and doesn't deserve a spot on any list. #Web Frontend#UI Design#Productivity

    My Portfolio

    RajShree1854TypeScript★6

  • D personal-newspaper-prompts A personal daily-notes style prompt collection, essentially a set of prompts written for the author, with no tooling, no evaluation and no indication of which models it suits. Prompt collections are already oversupplied, and this one shows nothing distinctive. #Prompting#Content Writing

    TJamesCorcoranLanguage unknown★8

  • D dualsouls A C# repo with no README; the name alone doesn't reveal what it does, and there are no verifiable usage instructions. #Games#3D#Animation

    igawa6C#★8

  • D curso-completo-de-kof A tutorial course repo related to the KOF fighting game, which is teaching content rather than a tool, so it isn't recommended under the rules. #Learning#Games#Content Writing

    lunalullyLanguage unknown★10

  • D SRMfullstack An undescribed repository whose name suggests a full-stack practice project for some SRM system. With no description or entry point, it can't be evaluated and doesn't count under the rules. #Learning#Web Frontend

    rishabinduction-ctrlPython★9

  • D sims-4-modmenu A The Sims 4 mod with unlimited money, unlocked items, and a cheat menu. It's a game cheating tool, which by the rules always scores low, and the 'for educational purposes only' claim doesn't hold. #Game Cheats#Games#Windows

    The Sims 4 trainer with infinite money, unlock all items, cheats menu, and build mode utilities. For educational use only.

    windloopexpiateC#★12

  • D smart-irrigation-system-using-iot-and-ai An IoT irrigation sample with only a title, no hardware, data sources, or run instructions; it offers no reference value to anyone seeking a reusable irrigation solution and belongs in the coursework category. #IoT#AI#Hardware

    smart-irrigation-system-using-iot-and-ai

    yudaysurendra-gifPython★9

  • D pembayaran_spp_laravel_react A Laravel + React implementation of a school SPP payment system, with an empty README, so it's unclear whether this is coursework or a reusable example. It explains neither deployment nor scope boundaries, offering no ten minutes' value to any reader. #Learning#Web Frontend#Databases

    AnamcoollzzTypeScript★19

  • D FlashClip No README description, and the name plus a C++ implementation aren't enough to tell whether it's a clipboard tool or something else. For readers of a ranking list, there is no evaluable information at all. #Productivity#CLI#Windows

    AyndpaC++★8

  • D eks-cluster The repo is named EKS cluster, but the README has no explanation, so it's impossible to tell whether it's a Terraform template, experiment notes, or coursework. No evaluable content. #DevOps#Linux#Automation

    DEVENDRA-5470Language unknown★18

  • D FireRedAudio No README description; the repo name suggests something audio-related (possibly TTS or audio generation), but nothing explains what it does, how to use it, or which models it depends on. Cannot be evaluated. #Audio#Speech#ML Research

    FireRedTeamPython★6

  • D Rudder-Swerve-Control No description; the name suggests steering-wheel or swerve-drive control code in C. With no hardware platform or control algorithm explained, it's hard for FRC or RoboMaster teams to reuse directly. #Robotics#Embedded#Hardware

    LYHrmerC★6

  • D L-Mechrove No README description, so it's impossible to tell whether this is mechanical design, embedded work, or simulation. There's nothing to evaluate. #Robotics#Hardware#Learning

    LiangyuLu-llyLanguage unknown★9

  • D Big-A-chovy No README description, and the repo name doesn't hint at its purpose either; just 0.1 days old with 10 stars. There is no information to evaluate. #Learning#Data Analysis#AI

    LuQTestPython★10

  • D opensew-2 The README contains only the word "Opensource" and doesn't even say what the project does; it's implemented in Python. There's no way to judge its purpose or usability. #Learning#Science#Data Analysis

    Opensource

    MarcelloMorettoniPython★6

  • D QQMiaoAssistant A zero-description repo where the name only hints at a QQ-related bot or assistant; features, dependencies, and startup instructions are all missing. It got a dozen stars on day one with nothing to back it up, so its purpose can't be judged and it can't be recommended. #Social#Automation#Plugins

    QiCaiJie114514Java★18

  • D Gen-AI-Agentic-AI An AI repo with no description at all; the name doesn't reveal whether it's notes, code, or coursework. With no entry-point explanation there are no users, and it's impossible to tell what problem it solves. #AI#LLMs#Learning

    Rathanam-06Python★8

  • D LinearAbilityExtThreeJS An undescribed Three.js-related repository whose name doesn't reveal what capability it extends. Without documentation there's no way to judge usability, and a dozen stars on its first day looks more like friends sharing it. #3D#Web Frontend

    achrefelouafiJavaScript★13

  • D Cross-Chain-Bridge-Arbitrage-Bot A cross-chain arbitrage bot with no description or documentation that gained a few stars within a day of creation. Such repos are usually star-farmed or paid-traffic bait, with risk far exceeding value. #Crypto#Blockchain#Scams

    heartstorkhatchetC#★6

  • D OpenDqrkis A Java repo with an empty README; even what the project does can't be confirmed, so it can only be skipped. #Automation#APIs#Plugins

    knezoWTFJava★6

  • D ai-quant-engine The description is just leftover text from an upload script, with no project explanation, and the tags don't match the content. A typical empty-shell repo. #Crypto#Fintech#Scams

    created by github-upload.ps1

    liugg-blipHTML★12

  • D readme Just a repository holding README templates, with no tool, documentation, or data value. Not worth a click. #Documents#Learning#Knowledge Base

    Place the README base

    miyanoyamiLanguage unknown★6

  • D Bybit-Copy-Trading-Signal-Bot An exchange auto-trading bot with "2026" in the title, closely resembling the same batch of OKX, Pump.fun, and MEV repo templates—likely star-farmed and possibly carrying private-key exfiltration logic. Don't run it, and never enter API keys. #Crypto#Scams#Fintech

    BybitBot — Bybit Auto Trader 2026

    validpolyestLanguage unknown★20

  • D OKX-Smart-Grid-Trading-Bot An OKX grid auto-trading bot whose wording is nearly identical to the Bybit, Pump.fun, and MEV repos in the same batch, suggesting a mass-deployed star-farming repo. The risk is key security and fund safety; not recommended. #Crypto#Scams#Fintech

    OKXBot — OKX Auto Trading Bot 2026

    victoriousconLanguage unknown★20

  • D Pump-Fun-Token-Sniper-Bot A Pump.fun front-running bot sharing the same template and wording as several trading bots in the same batch, a typical mass star-farming drop. Such repos often use 'free scripts' to lure you into handing over private keys; skip it. #Crypto#Scams#Exploits

    PumpSniper — Pump.fun Sniper Bot 2026

    vividragLanguage unknown★20

  • D Ethereum-MEV-Sandwich-Attack-Bot An Ethereum sandwich attack bot that profits by front-running other people's trades, which is outright predation on ordinary users. It uses the same template as the trading bots in the same batch, and the common trick is luring you to import your private key; don't touch it. #Crypto#Scams#Exploits

    MEVBot — Ethereum MEV Sandwich Bot 2026

    worldlyideoloLanguage unknown★21

  • D KERNEL No explanation at all; the name only hints at something kernel- or distro-related, and there's no telling what it does or whether it runs. Empty-shell repos like this usually go quiet within days and aren't worth ten minutes. #Operating Systems#Linux#Build

    OkraLinuxC★6

  • D roblox-script-keyless A Roblox cheat executor with ESP, flight, speed hacks and aimbot, carrying the usual 'for educational purposes' label. It damages other players' game environments and has no technical discussion value. #Game Cheats#Games#Anti-Cheat

    Roblox executor with script execution, ESP, fly hack, speed hack, aimbot, and unlimited resources. For educational use only.

    SupplierWallC#★8

  • D team-fortress-2-trainer A TF2 cheat offering aimbot, wallhack, and full weapon unlocks, with the usual "for educational purposes" disclaimer. It ruins other players' experience and has no technical value to show. #Game Cheats#Games#Anti-Cheat

    Team Fortress 2 trainer with aimbot, ESP wallhack, speed hack, no recoil, unlock all weapons, and infinite ammo. For educational use only.

    PlotPeasantCoveC#★6

  • D minecraft-cheat-script A Minecraft cheat bundle built on open-source clients like LiquidBounce and KiwiClient, whose main work is packaging. It's neither original nor suitable for public recommendation, and offers zero reference value to developers. #Game Cheats#Games

    Minecraft utility clients, hacked clients, and automation tools. Based on open-source projects like LiquidBounce and KiwiClient.

    TaloneouncoupleC#★10

  • D cyberpunk-2077-hack A Cyberpunk 2077 trainer with god mode, infinite money and weapon unlocks. It's a single-player cheat tool with no shareable technology, so it's out of recommendation scope. #Game Cheats#Games

    Cyberpunk 2077 trainer with god mode, infinite money, unlock all weapons, unlimited ammo, teleport, and sandbox tools. For educational use only.

    TyphoonchuoverpassC#★11

  • D r6s-wallhack-cheat An aimbot and wallhack for Rainbow Six Siege; claiming it's for learning doesn't change its purpose. It's a game cheating tool, so skip it. #Game Cheats#Games#Exploits

    Rainbow Six Siege trainer with aimbot, ESP wallhack, no recoil, triggerbot, speed hack, and unlock all operators. For educational use only.

    granitelakecycleC#★7

  • D Crypto-Clipper-BTC-ETH-SOL A cryptocurrency address replacer, a textbook clipboard-hijacking trojan, with no explanation beyond the implementation. It's malware, and no matter the code quality it should not be recommended. #Scams#Crypto#Secrets

    SentinelHorseLureC#★8

  • D Browser-Password-Cookie-Grabber A malicious tool that steals passwords and cookies from browsers, with no description and no legitimate use. It should never appear on a recommendation list under any circumstances. #Secrets#Scams#Privacy

    ViceCraftsmanC#★8

  • D Coinbase-Ronin-Rabby-Extension-Mapper The name strings together several wallets and browser extensions, yet there's no description—a typical suspicious crypto tool repo. Don't install it, don't connect a wallet, just skip it. #Crypto#Scams

    sectionmedicpinpointC#★8

  • D Discord-Token-Grabber-Webhook A Discord token stealer that hijacks other people's accounts and exfiltrates credentials via webhook—malware, not an open-source project. Such code has no legitimate use, and an unknown implementation may also steal your own data. #Scams#Secrets#Exploits

    nexuskazekagehumC#★7

Hot New Repos

  1. duty1g/x64dbg-mcp-server★1119 x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros
  2. b-nnett/grok-bot-0.18-reconstructed★932 Unofficial source-oriented reconstruction and extension of Grok Bot 0.18.0 for macOS
  3. tobi/walgit★764
  4. ShadowAqueduct/watermark-remover★763 Purge multi-vendor AI watermarks: clean Unicode text, apply statistical rewrite hooks, and clear C2PA plus metadata from PNG, JPEG, SVG, PDF, DOCX, HTML, and MD.
  5. nateherkai/scroll-craft★579 Claude Code skill for premium scroll-driven websites. Scroll becomes the timeline, on a real design floor, verified by screenshotting its own scroll.
  6. Forsy-AI/biosecurity-agent★512 AI agent that builds a live biosecurity world around any target.
  7. localai-org/kimodo.cpp★386 NVIDIA Kimodo ported to C++/GGML
  8. kgoedecke/doop★270 The open-source alternative to Paper.design. A multiplayer design canvas where humans and AI agents design together, live. MCP built in.
  9. bam-bam-2/solo-skills★226 One-person entrepreneur productivity kit — automated 49 tasks without employees, and releasing 26 ready-to-use AI agent skills (+ execution scripts) among them
  10. rome-os/rome★210 Rome is the agentic OS.

Star gain 1d

Data accumulating · 2 days needed, 1 so far. Snapshots build every day and the board lights up on its own.