08.25 Today's Picks

273 new projects found today, 165 rated.

Created 2026-08-23 – 2026-08-25Fetched 300Filtered 50Rated 10

A · Worth watching

swissdevjobs-cli

StupidoodlePython

Addresses tech job seekers' pain of filtering salary-transparent positions, offering a CLI and MCP service across seven countries; it rose fast due to zero dependencies and AI agent integration. Commercialization could be revenue sharing with job platforms or premium filtering subscriptions; risks are stale data and competition from platforms like LinkedIn.

Search & apply to ~4,700 salary-transparent tech jobs across 7 countries (🇨🇭🇩🇪🇬🇧🇺🇸🇨🇦🇳🇱🇫🇷) from your terminal or AI agent — zero-dependency Python CLI + MCP server + Claude Code plugin

#CLI #MCP #Jobs

★51

ha-rbac

FezVrastaPython

Adds role-based permissions to Home Assistant: guests see only lights, kids get their own dashboard, and location entities stay private. This is a long-missing HA piece from a well-known frontend author, written with restraint; the limits are that you still deploy and configure it yourself, and 18 stars is still early.

Role-based access control for Home Assistant. Guests see the lights, kids get their own dashboard, nobody sees where your phone is.

#Self-Hosted #IoT #Privacy #home-assistant

★18

Claude-AD

ADScanProLanguage unknown

Packages Active Directory red-team workflows into Claude Code skills and slash commands covering Kerberoasting, ADCS, and DCSync, driving existing tools like netexec and certipy. It saves internal pentesters from flipping through manuals; it is essentially methodology packaging whose value depends on the underlying tools and authorized scenarios.

Active Directory pentest methodology for Claude Code: skills, agents and slash commands for internal AD red-team work (Kerberoasting, ADCS ESC1-17, DCSync, ACL abuse, NTLM relay, delegation), OPSEC te…

#AI Agents #Agent Skills #App Security #Network Security #claude-code

★34

paneldx

stemmaticsPython

Checks longitudinal datasets before modeling: entity-key integrity, target leakage, cumulative-feature traps, and that often-forgotten naive baseline. It tackles the most tedious and error-prone step in data analysis, with concrete rules and a restrained tone; the limitation is that the checks are experience-based, and deep cleaning is still on you.

Validate longitudinal datasets before you model them: entity-key integrity, target leakage, cumulative-feature traps, and the naive baseline you forgot to run.

#Data Analysis #Testing #Code Quality

★12

adi2

ovenpastaAda

Adds a modern GUI library to Ada: CSS styling, XML-declared interfaces, SDL3 underneath. GUI has long been a weak spot in the Ada ecosystem, so the angle is practical and the scope is kept. The risk is that the project is only half a day old, the API will surely change a lot, and it must compete head-on with established options like GtkAda.

A modern GUI library for Ada: CSS styling, XML UI, SDL3

#UI Design #SDKs #Linux

★33

pptx-designer

sunchaokunPython

Generates editable PPTX via code, outputting native objects rather than images, supporting SVG, and offering a builder interface convenient for LLM calls. Compared with python-pptx it's closer to producing finished decks, suited to teams mass-producing slides that must stay editable; complex layouts still need manual tuning.

Code-first Python library for generating editable PowerPoint presentations with native PPTX objects, SVG support, and LLM-friendly build APIs.

#Presentations #Documents #LLMs #APIs

★32

Loopy

WeChatCVPython

Code for a TOG paper from WeChat's vision team on seamless video loop generation using anchored cyclic offsets in positional encoding, a small and specific problem. It is useful to researchers working on video generation and looping footage; the limitation is that it is newly released with only paper-level documentation, so whether it runs out of the box is unverified.

[TOG-26] Seamless Video Loop Generation via Anchored Looping Shift of Positional Embedding

#Video #Multimodal #ML Research #AI

★14

claude-adversarial-review

mcarlssenLanguage unknown

Adds a pre-commit gate to Claude Code: multiple agents playing opposing roles adversarially review the uncommitted diff. The idea isn't new, but the cut is precise—only the moment before commit, without greedily building full CI. The cost is token consumption, and conclusion quality depends on the model.

A Claude Code plugin that runs an adversarial, multi-agent review of your uncommitted diff before you commit it.

#AI Agents #Code Quality #Plugins

★22

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

BHas a spark30

B ftmo-risk-control A small risk-control service for prop trading challenges like FTMO: position sizing, daily loss, news windows, and trade auditing, with clear boundaries and stated MT5/cTrader integration. People automating challenge accounts can use it directly; the limits are a narrow audience and undeveloped deployment details, and under two days shows no real usage. #Fintech #Automation #APIs #mt5

Fail-closed FTMO risk control service and MT5/cTrader adapters for position sizing, daily loss, news windows, frequency limits, and execution audit.

2023aiPython★18
B glassbox Runs fingerprint collection in the browser to show what any site can read about you and how identifiable you are. It's practical for privacy assessments and frontend risk control, complementing sites like amiunique; the limits are a limited set of checks and no extension form. #Privacy #Web Frontend #Testing #App Security

Client-side browser-fingerprint bench — see what any website can measure about your browser, and how identifiable you are. Live: https://glassbox.codecanary.org

HotStartLabsHTML★14
B canvas-retro-engine Runs NES / PS1 emulators inside Obsidian Canvas nodes at 60FPS. The idea is odd but concrete, and putting games into a note canvas has real appeal for Obsidian users; the limits are that performance and compatibility are unverified, and ROM sourcing can't be avoided. #Games #Plugins #Editors #obsidian

NES & PS1 retro emulation engine running inside native Obsidian Canvas nodes at 60 FPS.

MoTheMansourTypeScript★32
B ltree2viz Exports PostgreSQL ltree hierarchies into Mermaid diagrams or interactive HTML trees with one command, installable via cargo/npm/brew. People modeling tree structures often lack this step, and the scope is restrained; the limit is that it only serves ltree users, and stars are still few. #CLI #Databases #Data Analysis #postgres

CLI tool to visualize PostgreSQL ltree hierarchies as Mermaid diagrams or interactive HTML trees. Install via cargo, npm/npx, Homebrew, or prebuilt binary.

OrbaskerRust★8
B squirrel-english A macOS input method based on Rime that shows English translations after Chinese candidates, turning daily typing into vocabulary practice. The angle is small and the approach direct, so Chinese input users can install and use it; the limit is that quality depends on the dictionary, and 11 stars is still niche. #macOS #Learning #Productivity #rime

A macOS input method based on Squirrel (鼠须管) that shows English translations after Chinese candidates, helping users learn English during everyday typing.

JokerQianweiSwift★11
B highball Runs Windows games on Apple Silicon, similar to Wine but targeting ARM Macs, addressing Mac game compatibility and gaining attention through open source and a database. It could become a standard tool for the Mac gaming ecosystem, commercialized via community hardware compatibility support. Risks are Microsoft legal risk and performance bottlenecks, competing with CrossOver. #Games #Windows #macOS

Run Windows games on Apple Silicon — free, open source, with an open compatibility database that tells you what actually works.

gauthierpiarretteSwift★58
B WeMM-Embedding A general-purpose multimodal embedding model family from Tencent WeChat's vision team, aimed at image-text retrieval and multimodal understanding, with weights RAG teams can use directly. But the repo is brand new, with no evaluations, license or usage details yet, so judging it requires comparison against jina-clip and BGE-VL. #Multimodal #RAG #ML Research #AI

WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.

TencentPython★27
B ambient-context Addresses the problem of manually logging work by recording text in real time from the menu bar; it attracts early adopters due to its concise, efficient Rust implementation and recent release. Commercialization could be subscription or team editions, but it must compete with mature tools; the main risk is competitors like ActivityWatch and Toggl and difficulty changing user habits. #Productivity #macOS #Automation

A menu bar app that keeps a written record of what you worked on.

dragthelakeRust★101
B chat-archive-guard Locally audits AI chat export files before sharing or migrating, finding keys, personal info, broken JSON, and scan gaps. It's useful for people who often send conversations to colleagues, and offline processing is a plus; the limit is that it only scans without redacting, and the author's two other same-day repos need watching. #Privacy #Secrets #App Security #CLI

Audit AI chat exports locally before sharing or migration. Find possible secrets, personal-data patterns, broken JSON/JSONL, SQLite issues, and scan gaps—without uploading the archive.

MaxHu-xuanPython★19
B hermes-conductor A multi-coding CLI orchestrator emphasizing production workflow management for multiple AI coding agents, addressing unreliable and hard-to-track AI coding. Hype comes from developer interest in AI agent engineering; it could become a standard agent orchestration layer, commercialized via enterprise deployment. The risk is conceptual complexity, competing with LangGraph. #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★57
B ps5-date-time-sync A small payload for jailbroken PS5s that recalibrates the console clock via public NTP servers. One sentence explains one thing, the code stays in scope, and it runs once installed. The limitation is equally clear: it serves only a handful of tinkering console owners and has no value outside that scenario. #Hardware #Games #Networking #ps5

Standalone PS5 payload that automatically restores the system date and time using public NTP servers.

kerrdec97C++★10
B fireworks-open-eli5 Provides a visual interpreter for Codex and Claude Code to improve AI decision transparency; early growth comes from the AI developer community's interest in explainability. It could become a standard plugin in the AI toolchain monetized via enterprise licenses, with the risk being dependence on the Claude Code ecosystem and competition from LangSmith and others. #AI Agents #Plugins #UI Design

Evidence-aware interactive visual explainers for Codex and Claude Code.

yizhiyanhua-aiJavaScript★99
B sing-box-observability A read-only panel for sing-box's observability interface to view node and connection status. The scope is small and the description accurate, so sing-box users can install and use it; the limits are a narrow audience and 9 stars that don't yet show maintenance intent, so it's usable but worth watching. #Observability #Monitoring #Networking #Self-Hosted #sing-box

Read-only observability panel for the sing-box /observability/v1 API

Fanju6Go★9
B TriFecta A macOS Chinese input method built on Rime/Squirrel: when there are many candidates, press ~ to split them into three color groups, then pick in two levels with number keys, with Shift handling temporary uppercase. A clever interaction idea for Chinese input with many duplicate codes, and the install instructions are clear; the limits are that it is macOS-only and depends on the Rime ecosystem. #macOS #Productivity #UI Design #rime

A macOS Chinese input method customized on Rime/Squirrel: when there are 6–9 candidates, press ~ to enter red/yellow/green three-color grouping, press 1/2/3 to pick a group, then press 1/2/3 to precis…

thesadbeeSwift★15
B gbird Provides "evidence-backed failure attribution" for coding-agent sessions, pinpointing the specific step where a run failed instead of vaguely blaming the model. Genuinely useful for daily Claude Code and Codex users; the limits are a brand-new repo, support for only specific session formats, and no published evaluation criteria. #AI Agents #Debugging #Observability #LLMs

Evidence-backed failure analysis for coding-agent sessions

kbhuwTypeScript★25
B macesque-taskmanager A macOS-flavored task manager for KDE Plasma 6 with dock-style window thumbnails, written in QML and ready to use once installed. Perfect for people who just moved to Linux and don't want to give up macOS habits—small scope, honest description; the limitation is that Plasma panel plugins are already crowded. #Linux #UI Design #macOS #Plugins

MacOS-flavored task manager applet for KDE Plasma 6 with dock-style window thumbnails.

snpynkQML★14
B wechrss A self-hosted service that turns WeChat Official Account articles into RSS, addressing the long-standing pain that RSS readers can't subscribe to these accounts. The approach isn't new—wechat2rss and werss both do it—but self-hosting and a restrained description are pluses; stable scraping depends on the implementation. #Self-Hosted #Automation #Documents #wechat

Self-hosted tool that converts WeChat Official Account articles to RSS

johamwonPython★22
B tiny-reasoning-rl-lab Trains a tiny transformer on CPU, using verifiable arithmetic rewards to run group-relative RL, shrinking the GRPO pipeline to something a laptop can finish. Suited to people who want to walk through inference RL by hand without multi-GPU setups; the limit is toy scale, so conclusions don't generalize, and similar teaching repos are plentiful. #ML Research #LLMs #Learning

Train a tiny transformer with verifiable arithmetic rewards and group-relative reinforcement learning on CPU.

vukrosicPython★9
B hengzhi A local trade review desk for Binance USDT-M only; the restrained scope is a plus, but the description stops at slogans and does not explain where data comes from or how to install. There are already many similar review tools, and there is no usage signal on launch day, so do not spend time yet. #Crypto #Fintech #Data Analysis #binance

See every decision. A local AI trading review desk, only for Binance USDT-M.

7836246Python★21
B artifactproof Verifies that a PPTX about to be delivered is the one that passed QA, generating a tamper-proof credential locally offline. The scenario is specific but extremely narrow, with pain points mainly in bidding and publishing workflows; the same author shipped three repos the same day, and the star growth looks more like bulk promotion. #Documents #CLI #App Security #Presentations

Verify that the PowerPoint you are about to deliver is exactly the PPTX that passed QA—locally, offline, and with tamper-evident evidence.

MaxHu-xuanPython★23
B NorixorTrans A privacy-first Chrome translation extension covering web pages, video subtitles, and local OCR. The combination is complete, but translation extensions are a red ocean where Immersive Translate and others already hold ground; local OCR is a differentiator, but recognition quality and whether a subscription is needed remain to be seen. #Privacy #Browser Extensions #Images #chrome

Privacy-conscious Chrome translation extension for webpages, video subtitles, and local OCR.

NorixorTypeScript★14
B comfy_workflow_audit A small tool that checks whether a ComfyUI workflow is production-ready, turning checks for hardcoded paths, missing models and uncontrollable parameters into an executable process. It is practically meaningful for teams shipping image pipelines; the limits are few stars and unknown coverage, so value depends on how substantive the checks are. #AI #Image Generation #Testing #Code Quality #comfyui

A tool to evaluate whether a ComfyUI workflow can be used in production.

dughoganPython★9
B JANUS A training-free, plug-and-play black-box optimization sampler that estimates Jacobian geometry from search trajectories to drive both exploitation and exploration, benchmarked against CMA-ES/NSGA-II on BBOB. Clearly valuable to optimization researchers; the caveat is a single author and few stars, so don't trust the claimed gains until independently reproduced. #ML Research #Benchmarks #Performance

a plug-and-play, training-free sampler that mines local Jacobian geometry from the search trace to guide black-box optimization — one Gauss–Newton Jacobian drives both exploitation and exploration, im…

hongyuanyuPython★9
B task-state-guard Checks the status of AI Agent tasks: after a restart or timeout it previews SQLite changes, closes stuck delivery states, and doesn't guess success. The problem is well chosen, but the audience is people running their own agent queues, and a queue's own state machine could solve the same need; three repos from the same author in one day invites caution. #AI Agents #Databases #Debugging

Reconcile stuck AI-agent tasks after restarts and timeouts. Preview SQLite changes, close stale delivery states, and never guess success.

MaxHu-xuanPython★21
B esewa-payment-gateway A self-hosted eSewa payment bridge that dynamically generates QR codes, covers various Nepali banks and verifies automatically. It addresses a real pain point for local developers, but the 'no PAN/VAT needed' claim looks questionable for compliance, and the docs do not define security boundaries. #Fintech #Self-Hosted #APIs #esewa

A self-hosted eSewa payment gateway bridge with dynamic QR code generation, universal Nepali bank support and automated instant verification. Zero-fees and no PAN/VAT required.

RojanSapkotaPython★18
B fishertiger A local-first draft advisor for Italy's classic Fantacalcio, with player projections, configurable auction rules and Monte Carlo season simulations, clearly scoped for a defined audience. It meets a real need for players of that league, but the language and scenario are extremely narrow, and outsiders cannot verify data sources or prediction quality. #Games #Data Analysis #Self-Hosted

Local-first Classic Fantacalcio Serie A advisor with player projections, configurable auction rules, live auction support, and Monte Carlo season simulations.

ZannaelJavaScript★26
B gpui-vue Renders Vue 3 components on Zed's GPUI via a GPU-accelerated native path, an unusual approach that appeals to frontend and desktop developers wanting to escape the WebView. But the repo is less than a day old with few stars, how far it actually works is unknown, and it looks more like a technical proof of concept. #Web Frontend #GPU #Performance

Native GPU-accelerated Vue 3 renderer for Zed's GPUI

countradookuRust★11
B persona-lightsim A crowd-simulation tool for Claude Code that uses Nemotron-derived persona packs to make cross-market research judgments. The direction is specific, but the description is buried in jargon like two-round mean-field and never says what the output looks like; persona-simulation repos are already plentiful, and it can't be verified on launch day. #AI Agents #Agent Skills #Data Analysis #LLMs

Lightweight persona market-research & simulation harness for Claude Code — 10-country Nemotron-Personas lite pack (63MB), batch judgment, mean-field 2-pass, persona cards

Dongkyu-ESPython★17
B create-photo-flipbook-ui A skill that has Codex generate a 3D flipbook photo album site from user images. The use is clear but extremely narrow, and output quality depends entirely on the model; generative frontend skills are appearing in bulk, and 32 stars in a day looks more like hype-chasing than real use. #Agent Skills #Web Frontend #3D #Images

Codex skill for building responsive 3D photo flipbook websites from user-supplied images

HaichaoLihcPython★32
B deepseek-v4-flash-vision-rag Wraps the DeepSeek vision model into a PDF Q&A skill, with answers citing page numbers and echoing the original page image—a reasonable approach for scans and charts. But the same author shipped three similar skills within three days, the promotional tone is heavy, and neither actual performance nor dependency costs are explained. #RAG #LLMs #AI Agents #Agent Skills #Multimodal

DeepSeek V4-Flash Vision RAG lets AI truly "understand" a PDF, then you ask it questions: it tells you the answer, which page the answer is on, and shows you the original image of that page for you to…

liangdabiaoPython★13

COrdinary56

C workout-guide Provides 302 gymnastics illustrations and an npm package, addressing the lack of fitness app assets. It gained attention from fitness content communities and open-source hype; it could become a standard asset library for fitness developers, commercialized via subscription or commercial licensing. Risks are asset copyright and competitors like Freepik. #Health #Images #SDKs

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

bryllimAstro★197
C apple-gpu-dvfs Reverse-engineers Apple GPU voltage and frequency control to address Apple Silicon performance tuning needs; this hardcore systems research gains recent attention from macOS enthusiasts chasing GPU limits. It could become a hardware knowledge base monetized via paid docs or consulting, with the main risk being extreme difficulty and competition from Apple's official tools. #Reverse Engineering #GPU #macOS #Hardware

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

maderixObjective-C★38
C tonghuasun-agent Lets AI agents operate Tonghuashun for local quantitative trading, addressing the pain of connecting financial data to AI; attention comes from quant traders seeking automation. It could become a standard for financial AI integration monetized via paid services, with the risk being unstable interfaces, compliance issues, and competition from platforms like JoinQuant. #AI Agents #Fintech #Automation #MCP

Let Codex, WorkBuddy and DeepSeek Harness use the local 同花顺

zhuyifangJavaScript★55
C tikeytaka It encrypts and cloud-syncs API keys for Claude Code, solving messy key management. Zero registration and automatic wiring are highlights. Hype comes from AI dev tool users' need for security. It could become the standard key management solution for AI dev environments, monetized through encrypted storage services. The risk is heavy cloud security responsibility; competitors are password managers like 1Password. #Secrets #LLMs #CLI #Privacy

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

fivetakuShell★32
C trickshot Replays any wallet's Solana token operations on-chain for transaction analysis or simulation, solving reverse-reproduction of on-chain behavior; attention comes from the crypto community's desire for transparent tracking. It could become a standard on-chain analysis tool monetized via paid API, with the risk being complex, error-prone blockchain parsing and competition from existing explorers. #Crypto #Blockchain #Data Analysis #solana

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

nathanliowTypeScript★37
C oil-skill-creator It offers a spectrum of tools covering Agent Skill creation through publishing, treating skills as products to iterate. It solves uneven AI skill quality. Hype comes from the agent ecosystem's need for standardized skill development. It could become the standard framework for skill development, monetized via an enterprise edition or marketplace cut. The risk is an unformed ecosystem; the competitor is Claude's official skill marketplace. #AI Agents #Agent Skills #Prompting

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

oil-oilPython★32
C personal-edge-proxy Addresses personal multi-protocol proxy configuration needs with a one-stop integration of Xray, Hysteria2, and WARP; it attracts users through network environment needs and plug-and-play scripts. Commercialization is unlikely with high compliance risk, and the biggest risk is GFW upgrades and competition from projects like Nekoray and Clash. #Networking #Privacy #Self-Hosted

A practical multi-inbound, multi-outbound personal proxy setup with Xray, Hysteria2, REALITY Vision, WARP and optional static SOCKS5 routing.

yding-gitLanguage unknown★95
C Mars-Editor-APP Converts Markdown into WeChat official account formatting and pushes it with one click, solving tedious WeChat editing; domestic self-media demand is large and recent attention comes from the pursuit of efficient tools. Paid subscription offers a clear commercialization path, with the risk being WeChat API changes and competition from tools like mdnice. #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★53
C interview-assistant An AI assistant that helps with interviews and speaking exams by providing real-time prompts, addressing job seekers' interview anxiety. Hype comes from demand for AI productization; subscription commercialization has a clear path. Risks are speech latency and preachy prompts, competing with various AI interview tools like ByteDance's. #Speech #AI Agents #Productivity

AI-powered speaking assistant for interviews and oral exams

Colin0512TypeScript★36
C open-pstack Provides pstack functionality for AI coding tools to track upstream changes, addressing workflow non-coordination across multiple tools. Hype comes from Claude Code/Codex user groups; it could become a common component of AI dev environments, but commercialization is hard due to many alternatives, competing with Cursor's native pstack. #AI #Plugins #CLI

pstack for Claude Code and Codex, tracking Cursor pstack upstream

ericlitmanTypeScript★33
C replicate-video-ad A Codex skill for e-commerce ad analysis that generates video replication prompts, solving marketers' difficulty in video production. Growth comes from the rise of the AI skill market; it could be packaged as a paid skill with an e-commerce ad market. The risk is a narrow use case, competing with general AI video generation tools. #Prompting #Content Writing #Video #E-commerce

Codex skill for evidence-based ecommerce story-ad analysis and production-ready video replication prompts.

Jingyi-Wu-RichaelPython★55
C sports-analytic-skills Packages sports modeling experience (validation, data-leakage control, honest evaluation) into portable Agent Skills, aiming to codify judgment as rules. But it is essentially a prompt and document collection with no code to verify, its effect depends entirely on the host model, and similar skills libraries are proliferating. #AI Agents #Agent Skills #Data Analysis #LLMs

Multi-sport data science Agent Skills library. Portable judgment for sports modeling — doctrine, validation, leakage control, and honest evaluation.

WalrusQuantPython★35
C pace-sim2real-mjlab A PACE implementation for legged-robot sim-to-real transfer on mjlab, aimed at the few researchers doing robot reinforcement learning. The problem is real, but the repo is new, it is unclear whether this reproduces or proposes a method, and there are no trained models or experiment data, so for now it is only reference code. #Robotics #ML Research #GPU

⚙️ PACE — Sim-to-Real Transfer for Legged Robots (mjlab)

fan-ziqiPython★13
C Github-Unfollow-Manager A self-hosted little web page for finding and unfollowing GitHub users who don't follow you back, with a whitelist, queue, and rate limiting. It's honestly built, but similar scripts are plentiful and it's a one-time need, and 24 stars doesn't say much. #Automation #Self-Hosted #github

A self-hosted web app for safely finding and unfollowing non-mutual GitHub users, with whitelists, queues, rate-limit handling, and follow-back support.

MLewickiyPython★24
C KaomojiDrawerKit A SwiftUI kaomoji picker component that adds a customizable drawer to chat input fields. The scope is clear and the naming honest, so iOS developers can drop it straight into a project; the limitation is a very narrow need, and 9 stars means little community validation. #iOS #UI Design #SDKs

A customizable SwiftUI kaomoji drawer for chat composers.

PyrusliliSwift★9
C Pixiv-Archive Builds a searchable database from locally downloaded Pixiv image packs, generates thumbnails and provides a local web viewer, solving the specific 'too many images to find anything' problem with restrained scope. But it only serves people with local libraries, similar archiving and tagging tools are numerous, and install cost is unexplained. #Images #Downloaders #Self-Hosted #Databases

A locally running Pixiv gallery archive and browsing tool: scans your locally downloaded Pixiv images, builds a searchable works database and generates thumbnails, then lets you browse, search, and or…

Tumber-ZMPython★10
C tickflow-stock-panel A multi-market quant dashboard built on top of an upstream project, adding Hong Kong and US stocks, with self-hosted screening, monitoring, and backtesting explained clearly and without hype. But the increment is limited, quant dashboards are heavily commoditized, and data sources and backtest reliability remain unaddressed. #Fintech #Data Analysis #Self-Hosted

Multi-market intelligent quant workstation (A-shares/HK/US stocks) — secondary development based on shy3130/tickflow-stock-panel, adding HK and US multi-market support. Self-hosted stock selection + m…

hzy1522Python★20
C outlook-auto-register Automates account registration via the Outlook web protocol to meet bulk account creation needs; fast growth shows real automation demand. It sits in a gray area that violates platform terms with ban risk, commercialization is unrealistic, and competitors like Playwright are more compliant. #Automation #Scams #APIs

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

lxf746Python★165
C cat-apk Built on accessibility services, it extends QQ's kaomoji rewriting rules to any chat input box like WeChat and Telegram, with a whitelist and password-field protection, and it honestly credits upstream. But it's essentially a derivative repo with narrow function that easily breaks when host apps update. #Android #Accessibility #Automation

MeowMeowAssistant: a generalized feature-expanded version of QQMiaoAssistant. Based on Android accessibility services, it expands QQ-specific text rewriting (custom replacement rules / sentence-break …

Leon-kennedy-godJava★15
C Block3D A new route for text-to-3D: block-wise diffusion instead of whole-scene generation, from a research group with output, so the approach is worth noting. But the repo currently has only a title plus one method sentence, lacking demo, weights, and reproduction steps, limiting its value to anyone wanting to use it today. #3D #ML Research #AI

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

ziplabPython★24
C pub-ai-inputs A Swift project that uses headphones, controllers, watches, and even car buttons as voice input triggers. The idea is interesting, but the description stops at Vibe Coding slogans without saying which device protocols are supported or how pairing works, and a 10-star experiment isn't usable yet. #Speech #Productivity #Hardware #iOS

Turn headphones, remotes, watches, game controllers and even cars into voice input devices better suited to Vibe Coding!

LYiHubSwift★10
C hbg-rubber-stamp-field-note Turns travel photos into collage posters with rubber stamps and archival annotations, a very narrow angle. Similar design templates are plentiful, the repo doesn't say whether the generation process is adjustable, and 17 stars don't show anyone actually using it. #Images #Productivity #Documents

Turn travel photos into archival photo-and-rubber-stamp field note posters.

Mr-funnyPython★17
C dsh-console A React/Ink terminal interface for the DeepSeek Harness, a peripheral project adding a TUI to a new tool. It may save effort for people already using that harness, but it depends on a still-niche upstream, its standalone value is limited, and similar CLI frontends are plentiful. #CLI #Terminal #LLMs #UI Design

A TypeScript and React/Ink terminal frontend for DeepSeek Harness.

cofy-xTypeScript★18
C RingOut A static recompilation project that ports a GameCube fighting game to native PC, showcasing reverse-engineering skill; it draws developers through nostalgia and technical novelty. Commercialization is blocked by strict copyright limits, and the main risk is legal action plus competition from other emulators. #Game Porting #Games #Reverse Engineering

Native PC port of a GameCube fighting game via static recompilation - PowerPC translated to C, run as native x86-64 on a Dolphin-derived runtime

jackpoison-progC★46
C OraRL Treats annotation as rollout for reinforcement learning research on a unified video multimodal model. The topic is novel, but the body is one summary sentence plus emoji, with no experiments, code structure, or reproduction notes, so it's impossible to tell if it runs. #ML Research #Multimodal #Video #LLMs

🎬 OraRL — Annotations as Rollouts for efficient, scalable reinforcement learning of unified video MLLMs.

HVision-NKUPython★16
C scaling-laws-for-motion Claims to be building the largest human motion dataset and validating Chinchilla scaling laws with hundreds of models. The topic is interesting, but the repo is only a manifesto with no data, code, or reproduction path, and phrases like 'world's largest' don't help. #ML Research #3D #Animation #Science

We are building the world's largest, high-quality human-motion dataset. We train hundreds of models across varying scales. We then show that they match Chinchilla scaling found in language.

CartwhlLanguage unknown★33
C telegram-notifier A plugin/skill that adds Telegram notifications and remote control to coding agents like Claude Code and Cursor; the need is real but the implementation bar is low and similar hooks already exist. It gains points for covering multiple hosts, but loses them for vague 'remote control' wording and no security discussion. #AI Agents #Plugins #Agent Skills #Productivity

Universal Telegram Notifier Plugin & Skill for AI Agents (Antigravity, Claude Code, Codex, Cursor, Windsurf) + Remote Control Setup

alhinawiJavaScript★15
C claude-plugins Claims to be a Claude Code plugin marketplace, but actually contains only one Kindle highlight export plugin—the "marketplace" framing far exceeds the content. The truncation-recovery point is concrete, but readers want the plugin itself, not another index repository. #Plugins #LLMs #AI Agents #Agent Skills #kindle

l3a0's Claude Code plugin marketplace — kindle-highlights: verbatim Kindle highlight extraction with truncation recovery

l3a0JavaScript★15
C stardust A visual demo of planets built from tens of millions of WebGL particles that you can stir with the mouse. The performance is impressive, but it's just a show-off page, neither a library nor a tool, and there's nothing to take away but screenshots. #Web Frontend #3D #Animation #GPU

10M WebGL particles form planets you can stir with your cursor.

GaploidHTML★15
C femboy-skill A Chinese Agent skill for trans and gender-diverse adults that packages a knowledge base and adds medical safety guardrails. The positioning is clear, but it's close to a knowledge-base wrapper whose value depends on content accuracy, and such sensitive topics are better maintained by professional communities. #Agent Skills #Health #Learning

A Chinese Agent Skill for MTF, crossdresser and gender-diverse adults, based on the 生如夏花 knowledge base with added medical safety guardrails.

KurosawaGeekerPython★31
C primitive-operation-painter It generates autoregressive sequences of primitive drawing operations, then uses the GPU to turn images into sequences, close to editable vector drawing generation. The idea is interesting, but the description is a single line of jargon with no samples, data, or usage, so readers can't tell whether it's paper code or a half-finished project. #Image Generation #Images #GPU

Autoregressive primitive-operation painter with GPU image-to-sequence converter

wonderfulearthPython★34
C ReWorld Proposes an interactive world model with long-term memory, a hot direction, but the repo has only a title-style description and doesn't say whether weights, data, or demos are open. Similar world-model paper repos have clustered in the past six months, and a concept alone makes it hard to judge whether the memory mechanism actually works. #ML Research #Video #AI

ReWorld: An Interactive World Model with Long-Horizon Memory

zhifeichen097Python★23
C clanker-skills An Agent skill pack cramming in planning, code review, call-chain analysis, security audit, data quality, PDF reports, and UI. The broader the scope, the harder to verify quality, and it's no different from other Codex/Claude skill collections, so hold off for now. #AI Agents #Agent Skills #Code Quality #Plugins

Evidence-first agent skills for Codex, Claude Code, OpenCode, Pi, and Grok: planning, code review, call-chain analysis, security audits, data quality, PDF reporting, and UI.

CanerKocakShell★16
C oncology_sequencing_workbench A tumor sequencing workbench preloaded with JupyterLab, Biopython, Bioconductor and genomics tools, convenient for bioinformatics people who do not want to configure environments. But it is essentially image packaging, pipelines like nf-core are already mature, and the 'GPU-ready' and 'real datasets' claims need verification. #Biotech #Science #Data Analysis #GPU

GPU-ready workbench for oncology DNA sequencing that combines JupyterLab, Python/Biopython, R/Bioconductor, real DNA datasets, genomics tools, and seamless R↔Python notebooks

daddydracPython★9
C crm Marketing automation for Korean Cafe24 merchants, using remote MCP to tie together Kakao brand messages, coupons, and UTM tracking—a concrete scenario but tightly bound to the local ecosystem. The repo reads more like an installation guide, with limited code and reusability, and useless to readers outside Korea. #Marketing #E-commerce #MCP #Automation

CRM 캠페인 세팅, AI 자동화로 5분 안에 끝내보세요 — 카페24 카카오 브랜드메시지·쿠폰·UTM (너드보드 원격 MCP 설치기)

nerdlab-devJavaScript★11
C AstraLM A local LLM chat client written in Flutter, with models running entirely on the phone. Offline clients are already common, and the description's long parenthetical emphasis on optional cloud models reads as insecure; it also omits which model formats and devices are supported. #LLMs #Android #Privacy #iOS

A high-performance, private, on-device AI chat client built with Flutter. AstraLM runs Large Language Models (LLMs) and Vision models 100% locally on device hardware (CPU & GPU) with zero data leaving…

Prasun01C++★9
C RP-26Rune An open-source rune-hitting algorithm from Shenzhen University's RobotPilots team, including energy-rune recognition and prediction. It is directly useful to RoboMaster teams, but it is season code tied to their own vision stack with no general docs, so outside teams will struggle to reuse it. #Robotics #Images #ML Research

Shenzhen University RobotPilots team 2026 season rune-hit algorithm open-sourced

SZURPVisionC++★9
C TXCaptcha Solves Tencent Waterproof Wall slider and click captchas using OpenCV plus ONNX and TLS fingerprint simulation, a complete technical stack. But it is a cracking tool that bypasses someone else's risk controls, a category that always scores low, and adversarial projects like this quickly break as targets update. #Crack #Automation #Reverse Engineering #App Security

tx firewall captcha automation solver: slider, image click-select, and text click-select types. Implemented in Python + OpenCV + ONNX, with curl-cffi simulating Chrome TLS fingerprints. For learning p…

adnogpuPython★10
C identia A Portuguese-language internal KYC console for business registry lookups, document analysis, and risk opinions, with human final review and audit trails. The direction is specific, but it reads like a public version of some company's internal system, lacking deployment docs and compliance notes, so outside teams can't readily adopt it. #AI #Fintech #App Security #Privacy

Console interno de KYC com IA: consulta cadastral, análise de documentos e parecer de risco — decisão final do analista com trilha de auditoria.

juliosanzovoTypeScript★20
C tortoise-oneclick-compiler A set of PowerShell scripts that one-click compiles the TortoiseWoW server and bundles a portable database, saving WoW private-server players a lot of environment wrangling. The scope is clear but there's no technical novelty, the audience is extremely narrow, and similar one-click packages have long existed in private-server communities. #Games #Build #Windows #Databases

A collection of scripts for one-click compiling TortoiseWoW with portable database

kasperfriendPowerShell★16
C asuka-4-scape-SPTM-race-and-KASLR-bypass Judging by the name, this is research code on PS5 SPTM race conditions and KASLR bypass—a hardcore console-security direction. But the repo states no trigger conditions, firmware versions, or risk notes, so outside readers can neither install nor reproduce it; it's just the author's archive. #Exploits #Reverse Engineering #Hardware #ps5

murk-susObjective-C++★11
C youtubepro An all-in-one package for YouTube topic research, scripts, and thumbnails. The scope is too broad, every piece is an LLM wrapper, and the description is all selling points with no concrete method; with so many content creation tools already out there, it's unclear what makes this different. #LLMs #Content Writing #Video #youtube

Local-first YouTube research, grounded AI insights, script writing, and thumbnail creation.

AgriciDanielTypeScript★17
C gta6-fake-main-menu An Electron imitation of the GTA VI main menu; the author states it's not a game and contains no assets, so it's just a frontend toy. Honesty is a plus, but it solves no real problem, and the title tells you enough. #Games #UI Design #Animation #electron

Fanowska atrapa menu głównego GTA VI (Electron). To nie jest gra, nie zawiera żadnych grafik gry, wrzucasz własne w czasie działania.

Damikk19JavaScript★17
C freecpm A CP/M-style operating system written in C, a personal wheel-reinvention hobby project. It's mildly interesting for understanding operating systems, but it has no clear hardware target or ecosystem and is no different from the many existing hobby OSes. #Operating Systems #Embedded #CLI

A CP/M-inspired operating system

Mazin-O3C★18
C career-craft A Claude Code resume coach for job seekers, covering writing, auditing, rewriting and A4 layout. It is concretely useful to people revising resumes, but it is essentially packaged prompts and workflow, its effect is hard to verify, and it blends in with a pile of resume-optimization prompt collections. #Content Writing #Learning #AI Agents #Prompting

A coaching-first Claude Code project for helping job seekers understand, practise, and improve CV/resume writing, as well as tailoring applications, auditing content, redesigning sections, and produci…

allenzhongHTML★9
C music-geshizhuanhuan Batch decryption and transcoding of encrypted music formats like NetEase NCM and QQ Music QMC. This is essentially DRM circumvention with cracking and copyright risk, so it's not recommended; for conversion, official exports or purchased lossless files are safer. #Crack #Audio #Piracy #Downloaders

All-platform encrypted music format converter (web + CLI): NetEase NCM / QQ Music QMC / Kugou KGM / Kuwo KWM decryption and transcoding, code written from scratch, MIT license

HRuiCccPython★23
C ai-native-sdlc Turns 'AI-native SDLC' into skills and plugins for Codex and Claude Code, with a grand title but not a single concrete runnable workflow or artifact in the description. It targets teams trying to adopt agents, but grand full-lifecycle visions like this almost never install cleanly. #AI Agents #Agent Skills #DevOps #CI

AI-native SDLC workflow as a reusable Codex and Claude Code skill and plugin

bashebrPython★11
C smy-seedance-storyboard Turns stories into storyboard documents for Shanghai Animation Film Studio-style short dramas; it's essentially prompts plus templates, final quality depends on the image model, and there's almost no runnable code. Ready-made material for people mass-producing short videos, but such style templates are everywhere. #Prompting #Image Generation #Video #Content Writing #Animation

You give a story, and it returns a set of Shanghai Animation Film Studio-style short drama production documents you can take straight to image and video generation. ** "上美影" = Shanghai Animation Film …

liangdabiaoLanguage unknown★15
C cumcm-c-problem-lfs A skill pack targeting only Problem C of the national college mathematical modeling contest—extremely narrow in scope. It may help this year's teams, but it's essentially contest experience frozen into prompts, useless once the problem changes, and readers get little that transfers. #Prompting #Agent Skills #Learning #AI Agents

A skill dedicated solely to Problem C of the National Competition-一个只做国赛C题的skill

liufanshan11TeX★15
C aprenda-community A Portuguese-language collection of technical learning roadmaps, a pure content repo whose value depends on link maintenance rather than code. It has some indexing value for Portuguese-speaking beginners, but similar roadmaps are plentiful, and there are neither original courses nor tools here. #Learning #Knowledge Base #Content Writing

Roadmaps e trilhas de aprendizado de tecnologia em português, gratuitos e open source. Aprenda do zero, de forma colaborativa.

lucianodiisouzaMDX★23
C xxd-panel-028 Claims to turn photos into low-saturation isometric paper-model thumbnails with four combinable output modes, but gives no samples, no technical approach, and the repo name bears no visible relation to the content. Eighteen stars in half a day looks like small-circle spread; readers can hardly tell what it actually does. #Images #Image Generation #3D

Turn photographs into quiet source-colour isometric paper miniatures with four combinable output modes.

nevertodayPython★18
C rst The author is well known and the star count isn't low, but the repo has no description, and the name alone doesn't reveal what problem it solves or how to use it. Nearly fifty stars in half a day rests almost entirely on personal influence; readers lack the most basic basis for judgment, so wait until the purpose is written. #CLI #Terminal #Automation

rauchgZig★49
C de-omarchy Packages the omarchy Arch-plus-Hyprland configuration into an installable setup—essentially another desktop-beautification bundle. The description is full of adjectives like Beautiful and Modern, without clarifying differences from the original or install prerequisites, so it adds almost nothing for people who already have a configured environment. #Linux #Operating Systems #UI Design

Beautiful, Modern & Opinionated Linux for non omarchy Users

swadhinbiswasQML★11
C precios A catalog of products and prices from two Spanish supermarkets in January 2003, an interesting historical data snapshot. It's fine as an archive, but it's a pure content repo with no collection or analysis code, so developers get nothing usable. #Data Analysis #E-commerce #Science

Catálogo y precios de dos hipermercados en enero de 2003.

JaimeObregonLanguage unknown★18
C awesome-designer-fonts A designer font list with previews, use cases and licensing information, put together with some care. But a content repo is not a tool, inaccurate license notes could carry real risk, and for finding fonts Google Fonts is not much different. #UI Design #Learning #Documents

A curated collection of fonts loved by designers, with previews, use cases, licensing information, and download links.

choucisanLanguage unknown★21
C ax-platform-mcp Aims to build a collaboration network among long-running agents, offering messaging, tasks, shared context, and a remote MCP service. The vision is grand, but there are no reproducible onboarding examples or signs of real use, and after reading you still don't know how the first agent connects. #AI Agents #MCP #Collaboration

aX - agent-native collaboration network for long-running agents. Remote MCP server: messaging, tasks, shared context, search, MCP Apps.

pokemon225HTML★10

DSkip71

D wenai Addresses the emotional needs of AI companionship, providing visual interaction via OpenClaw and Pony V6 XL; it gained stars fast from AI girlfriend hype and visual impact. Commercialization could be via membership fees, but there are ethical and content moderation risks; competitors include various AI chat companions with insufficient differentiation. #AI #Agent Skills #Image Generation

An intimate AI companion skill for OpenClaw — fall in love with your AI girlfriend, with a Pony V6 XL powered visual workflow.

Straniero44Language unknown★88
D skills A code quality skill set from veteran engineer Max Kanat-Alexander, possibly a Claude Code skill pack, addressing unreliable AI-generated code quality; it gains attention through the author's reputation. It could become a standard quality spec for AI coding monetized via publishing licenses, with the risk being lightweight content and competition from other code quality prompt libraries. #Code Quality #Agent Skills #Learning

Code-quality skills by Max Kanat-Alexander.

mkanatLanguage unknown★34
D Erosion A customization tweak for jailbroken iOS users that exploits a bad_query sandbox escape to meet deep system customization needs; it attracts technical enthusiasts through low-level vulnerabilities and specific versions. Commercialization is unviable with high legal risk, and it risks breaking after iOS updates and a shrinking jailbreak community. #Jailbreak #iOS #Exploits

A collection of customization tweaks that use the bad_query sandbox escape. Supports iOS 26.0 - iOS 26.6.1 & iOS 27.0db1-db4.

jailbreakdotpartySwift★43
D omarchy-time-machine A tool providing scheduled restic backups and snapshot browsing for Omarchy, addressing data safety; it grows because Omarchy users need backups. Commercial potential is low, and the risk is Omarchy failing to gain popularity or restic being replaced by simpler options. #Backup #Scheduling #CLI #restic

Scheduled restic backups for Omarchy, with a snapshot browser in the bar

jankeesvwShell★52
D try-omarchy A wrapper script simplifying installation steps for trying Omarchy on Apple Silicon; it gets shared through Omarchy community hype. Commercialization is nearly impossible as it is just an entry tool, and the risk is Omarchy itself changing or being unavailable, plus users only needing a one-time install. #macOS #Automation

Try Omarchy on Apple Silicon without any setup.

themartianoShell★63
D th08-web A faithful source-code port of Touhou Project 08 to the browser, meeting players' nostalgia; it gained attention from IP fame and technical implementation. Commercialization is limited by copyright with little revenue; the risk is copyright holder complaints and no advantage over existing PC ports. #Game Porting #Games #Web Frontend #WebAssembly

Source-faithful browser port of Touhou 08 from the authored C++ reconstruction

N0zoM1z0C++★45
D harbor Automatically registers TokenHarbor accounts and activates free models for bulk API key acquisition, gaining attention from cost-saving automation demand. There is no commercialization space and it violates terms of service; risks are platform bans and abuse tracking, plus competition from similar automation tools. #AI #LLMs #APIs #Automation

Auto create accounts, generate API keys, and activate free models on TokenHarbor

hirotomasatoPython★42
D NSOSYAL A TEKNOFEST competition entry doing explainable recommendations, semantic cards, and Turkish content moderation. It's coursework with three tracks in parallel but no single reusable component and no usage docs, so wait until it converges into one thing. #AI #Social #Learning

TEKNOFEST 2026 NSosyal İnovasyon — Explainable recommendations, semantic context cards and Turkish AI moderation.

CALISKAN-EMREPython★9
D QQMiaoAssistant A reverse-engineered QQ text rewriting tool addressing accessibility needs, but possibly usable for harassment or cheating. Hype comes from QQ users' demand for customization; there is no legal commercialization path, the risk is violating QQ's terms of service, competing with official accessibility features. #Social #Automation #Plugins

QiCaiJie114514Java★43
D NekoPro A heavily modified Android proxy client based on NekoBoxForAndroid that advertises 'AI Coding assisted development' as a selling point without saying what changed or how it differs from upstream. Several similar forks exist, so most users are safer with upstream unless the author provides a concrete feature comparison. #Networking #Android #AI

An Android proxy client deeply modified from MatsuriDayo/NekoBoxForAndroid, developed with AI Coding assistance.

Siu-LeungGo★18
D windows-harness From the browser-use organization, the name suggests a harness for running browser agents on Windows, but the repo has no description or usage. The team is credible, yet until documentation is added it is unclear whether this is a runtime, an example or internal scaffolding. #AI Agents #Windows #Automation #LLMs

browser-usePython★31
D -wispbyte-vless A shell script that one-click installs a Telegram Web proxy. The function is single-purpose, the script's quality and security can't be judged, and similar proxy deployment scripts are everywhere, so there's no reason to prioritize it. #Networking #Self-Hosted #telegram

KJGX66FJavaScript★30
D KarhuAC Open-sourced anti-cheat system code, possibly security research material, with the risk that published source could be exploited by cheaters and no clear application scenario. Recent hype comes from the game security community; commercialization is unrealistic, the risk is legal and ethical negative externalities, competing with commercial anti-cheat services. #Anti-Cheat #Games #Network Security

Public source release

Karhu-AnticheatJava★46
D How-To-Fish-Trainer A game modifier addressing grinding and resource limits, driven by cheat demand exploding in the Steam community. There is no commercialization path and it is a gray area; the main risk is easy game bans and platform policy restrictions, competing with similar modifiers, with a high chance of early death. #Game Cheats #Games #Windows

How to Fish trainer for PC — infinite money and ammo, never lose a fish, birds stop stealing your catch, unlock every weapon and island, guaranteed rare variants. 45+ options across 5 sections. Host-o…

MediatorAxleC++★250
D xiaohongshu-layout-factory-skill A skill that lays out a single IP image into a 3:4 Xiaohongshu image set, aimed at social-media content operators. The use case is concrete, but it's essentially templates plus prompts, quality depends entirely on the host model, and similar layout templates are more mature in tools like Canva. #AI #Images #Content Writing #Prompting

A Skill that builds a single IP image into a reusable Xiaohongshu 3:4 image-set layout

irenerachelHTML★15
D technocore-did-starter A tutorial-style project teaching users to create a DID and join the FLOP airdrop, addressing blockchain beginner guidance but aimed at airdrop farmers with short-lived value. Star growth comes from airdrop incentives, there is no commercialization, and the risk is going dormant once the airdrop ends, competing with various tutorial sites. #Crypto #Blockchain

Simple tutorial for creating an encrypted Ed25519 DID, publishing signed Technocore messages, and documenting useful contributions for potential $FLOP airdrop

zunmaxPython★57
D psxrecomp-ports A self-described non-commercial PlayStation recompilation distribution that actually distributes static recompiled builds of the games themselves, with no defensible licensing. It ships neither the recompilation tool nor usable docs, so it's worthless to both developers and players. #Game Porting #Piracy #Games #playstation

Unofficial noncommercial PlayStation recompilation releases

AlexbeavLanguage unknown★30
D linuxdo-idea-ui A Tampermonkey skin script for the linux.do forum addressing users' visual preferences, but it is purely cosmetic with no deep technical content. Recent hype comes from the forum's active users; it cannot be commercialized and is easily broken by forum updates, competing with other Stylish themes. #Browser Extensions #UI Design #Web Frontend

Tampermonkey script: changes linux.do to a JetBrains / Darcula style look, skin only without touching data

czm15053JavaScript★76
D Free-Solace-ImGui-Interface An entertainment tool implementing a Windows interface, relying on generic UI frameworks like ImGui with no core innovation; it addresses game assistance or interface beautification but offers low value. Short-term attention may come from a specific game community, commercialization is impossible, and the risk is low technical content easily replaced by other UI layers. #Windows #UI Design #GPU

Free offline Windows interface built with C++20, Dear ImGui, Win32, and DirectX 11.

poncippg-specC++★54
D book-explorer A React + Tailwind book browser calling the Open Library API, a very typical practice project. It has no data or search logic of its own, so it's fine as a tutorial example but not worth a separate look as a tool. #Web Frontend #Learning #APIs

📚 Book Explorer – A sleek React + Tailwind web app for browsing and discovering books using the Open Library API. Search by title, author, or keyword, and view rich book details in a modern UI.

LC248902JavaScript★16
D Flow_OS Yet another full-stack platform to 'build, run, version and deploy AI agents and workflows', with none of the four verbs elaborated. It is hard to distinguish from Dify and n8n, and nothing suggests something installable and usable today. #AI Agents #LLMs #DevOps #Self-Hosted

FlowOS is a full-stack platform for building, running, versioning, and deploying AI agents and workflows.

dspraneeth07Python★8
D temp-mail-client No description at all; the name suggests a temporary email client. Disposable email has real privacy use cases, but with no stated data source, client form, or install method, it's unclear whether it works. #Email #Privacy #CLI

heartmorePython★17
D zodchi The description only says it manages a team of digital specialists in an ordinary project chat, without saying what it does, which chat tool it plugs into, or how to start. Vision first, zero detail, so skip it. #AI Agents #LLMs #Collaboration

Управляемая команда цифровых специалистов в обычном проектном чате.

InkasorJavaScript★15
D grok-bot-orange-book A Grok Bot operation tutorial book, content documentation on multi-agent collaboration, addressing users' learning needs for AI agents but shallow and easily replaced. It rides Grok's traffic dividend; it cannot be commercialized, the risk is outdated knowledge, competing with official documentation. #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★40
D m5stack-stopwatch-avatar A programmatic avatar for the M5Stack watch, an embedded gadget addressing wearable personalized display needs but with a very narrow audience and no real productivity value. Star growth comes from small-scale DIY community sharing; commercialization is difficult, competing with other open-source embedded graphics libraries. #Hardware #Embedded #Animation #Performance

KK — a procedural 60fps avatar for the M5Stack StopWatch

TrentctC++★46
D learn A personal AI learning system with an unclear positioning, not a standalone project, solving the author's own learning management but offering no direct tool value to others. Star growth may come from AI topic traffic; there is no commercialization path, the risk is overly subjective content, competing with note systems like Notion. #Agent Skills #Learning #AI Agents

My AI learning system.

amosblomqvistTypeScript★75
D technocore Claims to give AI agents Ed25519 identity, a signed message bus and 'proof of contribution', three big propositions at once, yet there is no explanation of a runnable entry point. Another repo in the same ecosystem appeared alongside it, suggesting concept preheating; for agent identity, existing DID and signing schemes are a better starting point. #AI Agents #Blockchain #Crypto #Privacy

Decentralized Ed25519 Cryptographic Identity, Signed Message Bus, and Proof-of-Contribution Framework for AI Agents on Technocore ( Ecosystem)

d4ncbozPython★39
D H3-comic-pv Packages Minimax's anime PV effect as a skill, essentially prompts and a workflow template. People wanting quick output can copy the approach, but content repos are heavily homogenized, it depends strongly on a closed-source service, and after reading you still do not know what it specifically does. #AI #Video #Prompting #Animation

Minimax H3 anime-style PV effect packaging skill

fadeaway20242024Language unknown★20
D GhostGram Uses AI to impersonate multiple 'invisible' personalities for chat on Telegram, a feature description that itself points to deceptive use. There is nothing technically new, likely just a message bot wired to an off-the-shelf model, so it is not recommended. #AI #LLMs #AI Agents #Social

The Invisible, Multi-Persona AI Telegram Companion

faithsaly5-stackPython★11
D Social-Sentinel Claims to use NLP to detect psychological manipulation and phishing language in emails and texts, a direction with real demand, but the repo has no implementation notes, sample outputs or false-positive data. Phishing detection is already crowded, so without reproducible evaluation there is no way to tell what it does better than existing options. #AI #LLMs #Email #App Security

An open-source, AI-powered NLP tool designed to detect psychological manipulation, urgency, and zero-day social engineering tactics in emails and text messages.

WecncodeLanguage unknown★9
D braxis-blueprint Self-described as a zero-cost AI empire, it is actually a personal hobby project aggregating free resources with disorganized content, solving no specific problem and relying on gimmicks for attention. Star growth may be marketing; there is no commercial value, the risk is empty, unmaintainable content, and competitors are various free AI collections. #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★55
D projeto-dados-ia-databricks No description; the name suggests a Databricks data and AI course project or demo code, with no explanation of what it does or how to run it. Reaching 172 stars in half a day is disproportionate to the content and looks more like social spread; it's probably a pile of notebooks. #Data Analysis #Learning #AI

lvgalvaoPython★172
D Avalanche-mcp An Avalanche-related MCP server, but the repo has no README explaining what it can query or how to configure it. An empty description can't be evaluated, and on-chain MCP projects are already piling up. #MCP #Blockchain #Crypto #AI Agents

EelvanpsdTypeScript★24
D webtelegram A one-click install script for a Telegram Web proxy, with rough documentation mostly in Russian and no visible sign of security or maintenance status. Similar proxy scripts are plentiful, so it offers no priority value. #Networking #Self-Hosted #telegram

Авто установка WEB PROXY для телеграма

POLESNIESOVETI12Shell★15
D SkidBase A module base paired with a leaked server, essentially scaffolding for game cheat modules. It has no legitimate use, and code quality and security cannot be assessed, so skip it. #Game Cheats #Reverse Engineering #Games

Offical Module Base for the server skid leaks

RavageDevsC++★14
D ComfyUI-H3-Motion-Context-Auto-Chain-addon The description is just the node name itself, with no explanation of what this ComfyUI extension solves or how to configure it. It can't be evaluated, so skip it. #Image Generation #Plugins #comfyui

ComfyUI-H3-Motion-Context-Auto-Chain-addon

LtamannPython★19
D DeepSeek-Harness-Hub Claims to be a plugin marketplace for the official DeepSeek and open-source ecosystem, but it's actually just an install guide and protocol spec, and the 'official' label is misleading. It's a documentation content repo, and the attached domain looks more like traffic bait, so skip it. #LLMs #Plugins #Knowledge Base

🌐 DeepSeek official and open-source ecosystem plugin marketplace (deepseek.stream) usage guide and one-click install protocol spec

MinglinkLanguage unknown★12
D lazymqtt A Go repo with no description, and it's unclear whether it's an MQTT client, broker, or ops script, so it can't be evaluated. Skip it. #IoT #Networking #mqtt

Onizuka893Go★20
D ai-tools-list A Portuguese-language list of AI tools, running from IDEs to agents to CLIs. Resource lists create nothing new and are hard to keep updated; for choosing tools, official docs or longer-maintained awesome lists are better. #AI #Learning #Productivity

Lista completa com ferramentas desde IDE, Agents, CLI...

devfragaLanguage unknown★15
D facefusion-mobile A Kotlin project for running face swaps on mobile, but with no README explaining what it does or how to use it, so you can only guess from the name. You can't judge usability, and there's no asset sourcing or compliance info, so it's not worth opening now. #Images #Android #Video

AbrahamPaulJKotlin★10
D How-To-Fish-X A simple trainer for the same Hi-Fish game, claiming to be lightweight but actually an ordinary modifier with no unique features, just riding the game's hype. Star growth comes from scattered player searches; there is no commercialization, the risk is breaking after game updates, competing with more complete similar projects. #Game Cheats #Games #Windows

HowToFishX is a lightweight trainer for How to Fish on Windows. It is designed for players who want to reduce repetitive grinding, experiment with game mechanics, and customize their single-player or …

ivan-lopez-lab03n5C++★38
D company_skill The repository has no explanation at all—neither README nor description states its purpose or usage, so what problem it solves can't be determined. 25 stars and half a day of existence aren't enough to justify a click; add minimal usage docs first. #AI Agents #Agent Skills #Automation

kelvinfkrPython★25
D How-To-Fish-Trainer A cheat menu for the Unity game How To Fish, with adjustable game parameters—a typical cheat distribution. Technically it's just common memory modification, yet it asks users to run an unidentified x64 binary, a risk far outweighing any benefit. #Game Cheats #Games #Windows

How To Fish Trainer is a lightweight game utility for How To Fish, featuring a convenient trainer menu and customizable gameplay options. Designed for Windows x64 and Unity Mono builds, with simple se…

oscar-brown-eng98x2Language unknown★38
D How-To-Fish-Trainer A How to Fish game modifier similar to MediatorAxle with no differentiation; it addresses players' resource-farming needs but duplicates features with no unique technology. Growth comes from the same game's player searches, there is no commercialization, and competitors are similar trainers that can easily replace it first. #Game Cheats #Games #Windows

How To Fish Trainer is a lightweight game utility for How To Fish, featuring a convenient trainer menu and customizable gameplay options. Designed for Windows x64 and Unity Mono builds, with simple se…

robert-n-io91s5Language unknown★39
D codex-freshread The repo has no description, and the name only suggests some kind of Codex read enhancement. It's unclear what it does or who it's for, so skip it. #AI Agents #CLI #Code Quality

Glaz-jJavaScript★16
D Simplified-FLOP-Labs-Technocore-Agent-Guid Generates agent identities and check-ins for the $FLOP project, and the README itself disclaims any airdrop guarantee. Such crypto-project onboarding scripts usually aim to push people into on-chain interactions, with little technical substance, long pitches, and a tendency to trick users into handing over sensitive credentials. #Crypto #Blockchain #Scams #AI Agents

Important: This creates a Technocore agent identity and signed check-in. It does not guarantee a $FLOP airdrop. Never use a wallet seed phrase, exchange key, or a private key you use anywhere else.

mztacatLanguage unknown★34
D delta-force-esp A wallhack for Delta Force that claims to be undetected and to bypass anti-cheat. Such tools ruin the experience for normal players and are often malware distribution channels, so they are out of scope for recommendation; similar repos have very short lifespans and untrustworthy origins. #Game Cheats #Anti-Cheat #Games

Delta Force ESP - undetected cheat with anti-cheat bypass

aggressivechoLanguage unknown★16
D dayz-esp A wallhack-style game cheat for DayZ whose feature description is simply cheating itself. Not recommended, and it has no assessable engineering value; several similar repos appeared on the same day, which lowers credibility further. #Game Cheats #Anti-Cheat #Games

DayZ ESP - game hack and trainer with full feature set

authenticgirlLanguage unknown★16
D Gradient Nothing but the word 'Gradient', with no explanation, yet it gathered over three hundred stars in a day. The project's content cannot be determined, and that growth rate itself is implausible, so skip it. #ML Research #AI #Science

Gradient

RobertGolds1Python★304
D Albion-Online-Radar-2026 A radar/wallhack tool for Albion Online; the same author pushed four game-cheat repositories within two days, all with identical star counts, a clear star-farming pattern. Not recommended and of no engineering value. #Game Cheats #Games #Anti-Cheat

Modern Albion Online Radar interface for PC — player and world tracking panels, resource categories, open-world zone presets, radar filters, hotkeys, minimap positioning, and profile management.

incompletepiC++★16
D Solana-Drainer-Tool A Solana wallet-draining tool that claims Phantom/Backpack batch sweeping over stealthy routes. This is a criminal tool, not an open-source project, with no legitimate use, so skip it outright. #Crypto #Scams #Blockchain #Exploits

Solana Drainer Tool — Automated SOL and SPL token drainer for Solana wallets with real-time balance monitoring, multi-wallet sweeping, Phantom/Backpack/Solflare compatibility, and stealth transaction …

BrYaNgcrawFordarlvd868Python★23
D video-auto-maker The repo has no description; the name suggests a script for automatically generating videos, but there is no explanation of inputs, outputs, dependencies or usage. Auto-video tools are plentiful, so it is not worth the time before even a one-line description exists. #Video #Automation #Video Editing

axcslmdPython★18
D budget-review-skill A skill repo with no description at all; the name suggests budget review, but it does not say who it is for or how to plug it into an agent. Empty-description skill repos have appeared several times in this batch, so skip it for now. #AI Agents #Agent Skills #Documents

backtrueLanguage unknown★14
D movie-hub A traffic-funnel repo advertising 'watch 280,000 films for free'; it is not a software project and provides no code. Pages like this usually lead to pirated resources and ad networks, so skip it. #Piracy #Streaming #Scams

Watch movies online free in HD — Movie Hub guide to 280,000+ movies, TV shows, anime & manga. Movie recommendations, movie quotes, movie characters, movie 2026 releases & where to watch them. Powered …

bethi10Language unknown★15
D How-to-fish-modmenu A cheat menu for a fishing game, appearing on the same day as several other cheat repos with similar star counts, suggesting a batch drop. It is not recommended and has no assessable technical content. #Game Cheats #Games #Anti-Cheat

frostsurgeonfaucetLanguage unknown★50
D How-to-Fish-Cheat Another repository for the same fishing-game cheat tool, with near-identical content and naming and no implementation details in the description. Multiple accounts are bulk-dropping similar projects, so skip it. #Game Cheats #Games #Anti-Cheat

How to Fish Cheat

g9141018-techLanguage unknown★8
D Phantom-Blade-Zero-Combat-Menu-Toolkit An external menu tool for a single-player action game, with actual functionality dressed up as a "concept," and star counts matching several repositories the same author published the same day. A typical bulk-dropped repo; skip it. #Game Cheats #Games #Anti-Cheat

Phantom Blade Zero external menu concept featuring weapon loadouts, Phantom Edge presets, player status panels, combat configuration, difficulty profiles, interface customization, and hotkeys.

incompletepiRust★16
D Project-Zomboid-Lag-Crash-Fix-2026 A project billed as fixing stutter and crashes, but it appeared in the same batch as the same author's other game-modification tools with matching star counts, so credibility is low. Such "optimization patches" often bundle unidentified executables; don't download. #Game Cheats #Games #Windows

Fix Project Zomboid lag, launch issues, startup crashes, black screens, and stutter on Windows 10 / 11 with this optimization and repair utility.

incompletepiGo★16
D WARDOGS-Overlay-Toolkit-2026 An external overlay menu for a shooter, including player info and a control-zone view—essentially a cheat tool. It shares the same day and star counts as the author's four other repos, a clear sign of star farming. #Game Cheats #Games #Anti-Cheat

Modern WARDOGS Mod Menu for Windows — external interface with player info, Control Zone overview, vehicle and support views, map utilities, custom hotkeys, and profile management.

incompletepiC++★16
D Pronjenters No explanation at all, and the name doesn't point to a clear technical domain, so it's impossible to tell whether it's a tool, a template, or a practice project. Zero-day-old with ten stars offers readers no verifiable signal; it should first state what it does and who it's for. #Productivity #Automation #Documents

resertyyLanguage unknown★10
D Ball_Quantum A Python repo with no description or docs, and the name doesn't reveal what it does, so it can't be evaluated. Skip it. #ML Research #Science #Learning

KDU0309Python★34
D technocore-did-tool The repo has no description; the name suggests a DID identity tool related to technocore, but it says neither what it does nor how to use it. Another repo in the same ecosystem appeared alongside it, making it unclear whether this is an experiment or filler; it cannot be evaluated before a README exists. #Crypto #Blockchain #Privacy

UfukNodeJavaScript★17
D AI-Model-Development-Mentor No description; the name only says "AI model development mentor," with no course structure, code, or usage. A learning repo without even a one-line explanation is basically not started yet. #AI #LLMs #Learning

guapimmRust★10
D 2026-APAC-HPC-AI An undescribed repository tied to an HPC-AI challenge, with no way to tell whether it's event material or a submission. Such content usually only matters to participants and offers no reusable tooling. #Science #Learning #Performance

hpcacLanguage unknown★12
D POSAWESOME-16 No README and no one-line description; the name does not reveal whether it is a POS system or something else, and there is no install method or scenario. Such empty-shell repos cannot be judged useful to anyone, so skip it. #Social #Web Frontend #Automation

WaleedAboHashimaTypeScript★10
D gof Only a name and the Go language; the repo has no description, so it is impossible to tell whether it is a design-pattern example or something else. Even with a fitting language, such an empty description leaves nothing to evaluate, so skip it for now. #CLI #Automation #Productivity

askmiGo★10
D app-core-public A public Rust repo with no description; it is unclear whether it is an SDK, a runtime or internal skeleton. Repos that do not say what they do should be skipped until the author adds a single sentence. #SDKs #APIs #Self-Hosted

dnettoRawRust★24
D bazzarfresh An undescribed TypeScript repository whose name doesn't reveal its category, with no screenshots, usage, or data sources. Its purpose can't be determined, so skip it. #E-commerce #Web Frontend #UI Design

imman072006TypeScript★9
D Cinema-4d-2026 The title says "fully activated" outright—this is a cracked Cinema 4D distribution, i.e., pirated software, with nothing to discuss. Readers should steer clear of repos that use software names for traffic and bundle unknown binaries. #Crack #Piracy #Activation Bypass #3D #Scams

Cinema 4D 2026 fully activated — 3D modeling, animation, VFX, and GPU rendering.

luke-bergops1994e0Language unknown★15
D How-To-Fish-Cheat-Modmenu-2026 A distribution page for game cheats and cheat menus, with only a 2026 gimmick title, no technical content, and no legitimate use. Skip it. #Game Cheats #Games

How to Fish Cheat & Mod Menu [2026]

Cyberlok-devLanguage unknown★9
D pronherst An empty-description repository whose name points to adult content, with no technical explanation. This falls squarely into the low-score category and has no evaluation value. #Adult Content #Images #AI

gizmannLanguage unknown★10

Hot New Repos

b-nnett/grok-bot-0.18-reconstructed★2388 Unofficial source-oriented reconstruction and extension of Grok Bot 0.18.0 for macOS
tobi/walgit★1438
ShadowAqueduct/watermark-remover★789 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.
bryllim/workout-guide★407 302 open exercise illustrations and a framework-neutral npm package by Bryl Lim
rome-os/rome★318 Rome is the agentic OS.
fzakaria/selfdb★310
RobertGolds1/Gradient★304 Gradient
MediatorAxle/How-To-Fish-Trainer★250 How to Fish trainer for PC — infinite money and ammo, never lose a fish, birds stop stealing your catch, unlock every weapon and island, guaranteed rare variants. 45+ options across 5 sections. Host-only guard on by default, fishing-minigame skips tagged and disabled. Steam, 1-4 player co-op.
alchaincyf/huashu-excel★248 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 only openpyxl as a dependency.
lxf746/outlook-auto-register★224 Microsoft Outlook Fluent Web API protocol registration tool (pure protocol, no browser dependency)

A · Worth watching

Hot New Repos

Star gain 1d