#Automation
200
2026-10-01
feder-cr/dots
S
Open-source dots for the web: an AI agent with its own browser, one that does not get blocked.
2026-09-20
Show HN: CUA-S1 – A System One Model for Computer Use
S
Hello HN! We're Dillon and Francesco from Cua. We were wondering how many computer use tasks actually need a full general purpose LLM (e.g. gpt-6-astra, claude-opus-5 etc.) to think through all their decisions and steps. Some tasks require thinking about a plan, exploring different paths, recovering from failure. Other tasks are a question of making local decisions, like this value should go in this box, or should I check this box, or this element should be ignored. We wondered how far we could go with a small model trained to only make these kinds of decisions. Our inspiration was Typesafe's Jev and its System One Model framing. This is a nod to the dichotomy between thinking quickly, automatically, and intuitively (system 1) vs. thinking slowly, analytically (system 2), as described by Daniel Kahneman. The interesting question for us was: what happens if you give a model an interface of current context, and a set of possible choices, and you ask it to return a probability for each choice? This kind of model does not generate output token by token like most LLMs do, but rather scores the options you give it, which you can check, trust, and use to drive your app's behavior. CUA-S1 is our answer for narrow, specialized decision models for computer use. Our first release is CUA-S1-FORMS. We built this from ideas and code in jevlike, and then trained a second model just to handle form interactions. It has 706k parameters, and the original checkpoint is 2.8 MB. The first training iteration took less than 30 minutes on synthetic data. Given a set of structured elements and values extracted from a document, it predicts whether to use the given value, CHECK, CLICK, or SKIP for each element. It does not predict new values for text fields, and does not consider screenshots. Element decisions are scored together, and your code can order the actions, and Cua Driver will execute them one at a time. A first evaluation of this specialist vs. hosted Jev on our form task: - For the whole decision set: 99.7% correct vs 83.6%. - For the subset of steps that require an action: 100% correct vs 96%. - For the subset of steps that are just leaving already-filled fields alone: 100% correct vs 74%. The specialist was trained specifically for this task and convention (just press skip for already filled boxes), while hosted Jev has not been fine-tuned for it, so this is an experiment in scoped specialization. We measured 7-9 ms to score a form locally vs. 260-280 ms per call to hosted Jev including network latency, though those samples measure different things and are not end-to-end form completion times. Our interest here is in the space between a brittle script and a general agent loop. The content and layout of form fields vary enough that scripts get unwieldy, but the set of available decisions can remain narrow and well scoped. We want to explore the possibility of a general agent encountering something novel, and passing well understood decisions over to specialists like this. That is a direction we are looking into. The current release is for forms only. We're open sourced the synthetic data generation, training, evaluation, and Driver integration under libs/cua-s1 with an MIT license. Comments welcome! Especially if you are building computer-use agents and have run into a recurring decision that is too variable to script but is too narrow to call another LLM for.
2026-10-13
onehumanbeing/esp32-iphone-agent
S
Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.
2026-10-11
aindeev/agent-chrome-relay
S
Let your AI agents use your Chrome, signed in as you, in background tabs. By Alexey Indeev · blog: read.aindeev.com · X: @AlexeyIndeev
2026-09-01
Show HN: 49 IDE – 2D Canvas for Agents
S
Track agentic CLIs across multiple providers and repos, from any device and across multiple machines, see git trees, terminals, usage, issues, and UI all on one workspace. I have been trying to parallelize agentic coding to extreme, sometimes managing up to 15 CLIs at the same time across multiple repos and tasks, and I suffered a huge productivity tax due to context fragmentation and constantly forgetting which terminal is doing what. I felt restricted by most grid pane managers, and thats why my friend and I built 49 IDE.
2026-08-28
sapientinc/PRAXIST
S
Autonomous research system for measurable, computer-executable research.
2026-10-16
feder-cr/open_scion
S
Open-source version of Scion: version control built for coding agents.
2026-09-03
dreamers-laboratory/agent-fleet-manager
S
A general-purpose engine for large-scale, repeated information gathering by a fleet of workers.
2026-10-15
outcrawlai/scout
A
Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository.
2026-08-29
XiaoDuoYa/codex-with-chatgpt
A
ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
2026-09-25
Show HN: PlaceCall (YC W26) – agentic API to call businesses and get things done
A
Hi HN, this is Yarik and Vlad from VOYGR - we are building the tools for agents and apps to engage with local businesses. It all started with our own pain point at VOYGR: calling businesses to verify if they are open. We are both from Google (Maps and Search) and even there, the merchants and venues don’t keep this info updated. So we built an API and started using it in-house. On July 4th, we were driving through Portland looking for a place to eat. Google Maps was saying “Holiday hours may vary”. We tried some AI assistant apps (Poke was trending back then), and they couldn’t help. Our API found 15 Thai and sushi places and called it in parallel. A few confirmed that they are open today and are taking walk-ins. One was marked closed on Google. The app can find the restaurant, but someone has to answer the phone. This is the problem we kept seeing. Assistants can’t do much in the real world where the phone number is still a major communication interface. Muse added calls in beta mode, but it’s still calling only one place at a time. There are a bunch of tools to create your own voice agents, but nothing that can work simply out of the box. We’ve built PlaceCall to fit all your agentic needs. Give it a task in plain English and a US phone number (or a list of numbers) - it navigates phone menus, waits for you on hold, and returns a structured response with outcome, recording and transcript. If you don’t have a phone number, just describe what you need and PlaceCall comes up with the recommendations. Here is the demo: https://youtu.be/7ZbVCPv8Wq0?si=LoLxxx1M7nhS7_j- When PlaceCall API was tested in our hackathon, we had the following use cases implemented by the developers: checking if a doctor accepts new patients, getting quotes for car service, and running quick surveys. The API can be used through Claude Code and Codex; examples and setup are listed in the repo: https://github.com/voygr-tech/placecall We give the first 250 calls free. Product page is here: https://voygr.tech/placecall/ Try it and let us know how it goes. We are interested in learning what you would use it for and what is missing. We are here all day and happy to answer any questions. Our email: [email protected]
2026-09-09
Colafornia/short-video-generator-AI
A
Free open-source project designed for turning youtube-viedos into viral short videos. Highlight detection, subtitles, translation, voiceover, all in one for your content.
2026-11-08
shanselman/sandbox-mcp
S
Fresh, throwaway Windows machines for testing your apps: an MCP server and CLI that automate Windows Sandbox
2026-10-13
madeyexz/louisa-wifi
S
Automatically connect to the Wi-Fi at any Louisa Coffee in Taiwan (macOS menu bar app + Raycast)
2026-10-10
robbin/android-adb-control
S
An Agent Skill for Android phone control via ADB: observe, act, and verify. For Pi, Codex, Claude Code, and OpenCode.
2026-09-11
mizzlelover/gongwen-gbt9704-skill
A
Cross-platform Chinese official document typesetting Skill that generates editable DOCX following GB/T 9704-2012
2026-08-29
usedotai/dot-reflex
A
Open-source agent execution-recovery controller for coding and tool-using AI agents.
2026-09-05
Show HN: TERMy – A fast terminal assistant that does not use LLMs
A
I love research and development, you may have heard of me because of PJON (Padded Jittering Operative Network). It is a network protocol I started developing in 2010, which was recently implemented in silicon by the ETH Zurich university thanks to the research of Pius Sieber. I am excited to share with you TERMy, a terminal assistant built on top of the NPC-Forge framework. Unlike everything else being built today, TERMy does not use embeddings, machine-learning or LLMs. It runs on the CPU (even on a Raspberry Pi Zero) both in the terminal or client-side in a browser tab and responds in milliseconds. It is a cynical but very knowledgeable Linux terminal assistant that translates your natural language into shell commands without relying on a single artificial neuron. I had a chance to focus for 2 months on my personal projects since early July, during the strange times of AI price hikes and the end of subsidized tokenmaxing. I was curious to see if I could develop from scratch a terminal assistant capable of handling simple natural language requests. I have a bad memory and got used to ask to copilot "activate the virtual environment" or similar trivial operations spending a non negligible sum every month. I started thinking, maybe I can do something to make my workflow more efficient? Do I really need trillions of parameters to accomplish those tasks? How it Works When you type a prompt, it goes through a lightweight NLU pipeline written in ~1000 lines of Python that implement the following steps: 1. Strip expletives, interjections, encouraging, discouraging and thanking words (remove noise) 2. Sentiment analysis 3. Exact Match (very fast) 4. Template Match (slower) 5. Probabilistic Match (even slower) Step 5 relies on: 1. IDF (Inverse Document Frequency) to identify rare words. 2. BOW (Bag Of Words) to accommodate word inversions. 3. IDF weighted Levenshtein to safely handle typos. Permission gating is hardcoded into the dataset and enforced for all potentially destructive commands, so it's inherently safer than letting an unpredictable LLM run wild on your machine. - TERMy in operation: https://www.youtube.com/watch?v=qeIp0xePLBg - Variance and typo tolerance: https://www.youtube.com/watch?v=tQvGDk6fkk0 - Copilot integration: https://www.youtube.com/watch?v=Wzzouhq2a8A - Advanced features: https://www.youtube.com/watch?v=qeIp0xePLBg - Source Code: https://github.com/gioblu/NPC-Forge
2026-11-08
lxe/phoneuse
S
See and operate an unmodified iPhone from a Linux PC: AirPlay mirror in, Bluetooth HID mouse/keyboard out, plus a CLI and skill for agents.
2026-10-09
Pama-Lee/MacMiniMode
S
Keep a plugged-in MacBook awake with the lid closed: clamshell mode without an external display, auto-off on battery. Let a MacBook stay awake with the lid closed and use it like a Mac mini.
2026-09-09
Lakr233/maintainable-update
A
Repo-wide maintainability sweep: copy, clarity, wrap, width, split, rename, tidy
2026-08-23
zhaoxuya520/MeshLAN
A
Self-hosted P2P-first virtual LAN, service sharing, multi-relay and AI automation built on Nebula.
2026-09-30
KKKKhazix/AIHOT
A
A website framework that finds trending topics on its own and writes its own daily digest. Swap in your own sources and curation criteria, and it becomes your industry trending site.
2026-11-04
Balanov/skein
A
Fail-closed swarm orchestration with epoch-fenced work and late-completion rejection.
2026-10-21
Show HN: VoidAccess – open-source dark web OSINT, from query to a graph
A
Hi HN! Im Katriel, and im a Security Researcher/Enthusiast and in the wave of AI, i wanted to build that next gen of security tooling that surpasses the current tools, and even the paid industries with an open source engine. I built MailAccess as well, which is going to be the best damn email osint tool out there, in another year. But just before building MailAccess i built VoidAccess, because i was delving a lot into DarkINT and the content inside the dark web is too difficult to navigate through for a human, so i automated that pipeline, made sure the noise was removed, and anything NSFW was filtered out, to give the analyst an overview of what is present in the dark web, without having to actually go through it manually. Very simple to run, you just run a few commands to install, and a couple to investigate. Then the engine takes over, and stops onyl when the job is done(or at a particular time limit, if set by the user). Do check it out, if that is something that interests you. Thanks to the community for giving it the love it has got till now.
2026-09-05
KJGX66F/usque-custom-pro
A
A visual registration, config generation, and multi-client conversion tool based on Cloudflare WARP / MASQUE. Generation, Clash/Mihomo smart routing, Shadowrocket, sing-box, local VLESS bridging, and optional WARP egress detection.
2026-08-23
dbl8005/sitrep-panel
A
A live local HTML report Claude keeps updated as it works — status board, running narrative, screenshots, newest-first log, live-reload. No cloud, no build step.
2026-09-07
alchaincyf/huashu-mac-use
A
Let any agent control native apps on Mac that have no API: read the background, write without disruption, keep evidence at every step · Agent Skill for macOS computer use
2026-10-26
wangrongding/tv-fresh
A
tv-fresh TV refresh: an Agent Skill for Xiaomi TV (MIUI TV) to remove ads / clean preinstalled apps / change launcher / install proxy and media repos — root-free and reversible, with firmware reverse-engineering notes and one-click scripts
2026-10-22
xingjian-bai/opal
A
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
2026-10-17
alonehobo/1c-cf-vendor-merge
A
Skill for AI agents: updating a customized 1C configuration to a new release via three-way git merge of XML dumps
2026-10-11
xcgtb/StrimKeep
A
A NAS-oriented STRM dual-library movie and TV management and governance tool, supporting quality-based selection, missing-episode comparison, movie/TV discovery, follow-and-subscribe updates, and library notifications.
2026-09-23
FluidInference/FluidUse
A
Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Accessibility API
2026-09-17
Show HN: Give your AI agents access to WhatsApp
A
Hi, I built Chat-Man because I wanted a cheap way to give my agents access to WhatsApp without integrating a WhatsApp library separately in every project. You get WhatsApp MCP server, so you can connect WhatsApp to an agent and programmatically read, search, extract and send messages - but also have a web UI for non-techies. You can also receive webhooks for incoming messages for starred conversations. What you can do with the MCP? -Read WhatsApp messages and turn them into CRM records -Summarise conversations or groups -Extract structured information from messages -Find messages, participants or other WhatsApp data -Send messages -Manage group memberships Of course.. you always need to follow data protection regulation. The web UI: -Edit group details -See who joined or left -See who is most active -Export group members -Match members against a CSV (e.g. from a CRM) -Bulk message members -Bulk kick members -Create invite links For individual contacts, you can send messages directly from the UI. Why I built it for myself? I needed WhatsApp access for several projects (hermo.ai, florahaus.co.uk, …) and didn't want to pay for a WhatsApp integration for each project. Link: https://chat-man.net I’d love to get some feedback, especially from people building agents that need access to WhatsApp. Fabian
2026-08-24
w-partners/Wbrowser
A
Drive the Chrome you are already logged into - from your terminal or any AI assistant. Cross-platform, MCP-ready.
2026-11-05
Balanov/latch
A
One tiny HTTPS contract between any agent and any service. Quote, approve, commit, receipt. Zero dependencies. MIT.
2026-11-05
Clahen86/ha-replace-device
A
Replace a dead device or move many from ZHA to Zigbee2MQTT – the new one takes over names, entity IDs and history
2026-11-02
rejig-app/rejig
A
Mac app for arranging your iPhone Home Screen over Wi-Fi or USB, with a change list, backups and readback.
2026-10-23
golbin/rekey
A
Reissue an API key with one command and update it everywhere it is used (1Password + templates)
2026-10-09
LingCore/WinShun
A
A fast search launcher for Windows: double-tap Ctrl to summon, search by filename, pinyin and text content. Qt 6 + C++20.
2026-09-28
gulelmatthews/Polymarket-Perpetual-Bot
B
Polymarket trading bot for prediction markets — browse CLOB markets, watch the order book in the terminal, run edge detection, liquidity provision and cross-market arbitrage strategies with paper trading and risk limits. Educational open-source toolkit — not financial advice. Unofficial community project, not affiliated with Polymarket.
2026-09-22
seifreed/renfecli
A
CLI no oficial de Renfe, pensada también para agentes — horarios y tarifas reales de tren desde la terminal
2026-11-09
Goblinmine/homelab-diagram
A
Renders an r/homelab-style network diagram from a YAML inventory (Python → SVG/PNG). Written with Claude.
2026-10-30
johncassil/dontallow
A
Auto-dismiss the macOS 'Allow X to find devices on local networks?' prompt. Presses Don't Allow for you, zero CPU idle, survives reboots.
2026-10-25
semsturgut/open-iphone-use
A
Give AI agents a real iPhone through macOS Bluetooth HID, local screen sharing, and MCP.
2026-10-24
man15h/tellyscope
A
Debloat your Android TV, install apps, and browse and transfer files on it, all from your phone. Under 3 MB, no tracking, no root, no PC, no AI.
2026-09-24
saragordic/rooms
A
Switch between projects on your Mac. Every project is a room: its windows, laid out, one shortcut away.
2026-09-23
deepakness/cogsend
A
Self-hosted social media scheduler. Write once, publish to any connected platform. Runs on your own Cloudflare account.
2026-10-24
cpypwn/mac2jb
A
Use your Apple Silicon Mac as a USB HID keyboard to transfer the ns2jb bootstrap and automate post-bootstrap commands on Nintendo Switch 2.
2026-10-07
nickvasilescu/bops
B
Bops: a team of AI bots that run your business ops, each with its own computer, email and phone number. bops.bot
2026-09-29
kofiadeyemiq/shellstrict
A
Lint shell scripts for missing strict mode and for mktemp files with no trap cleanup, complementing ShellCheck.
2026-09-22
logabell/dewarr
A
Self-hosted audiobook discovery, Goodreads and Hardcover lists, Audiobookshelf integration, and automatic downloads.
2026-09-04
agentthink/sim-foundry
A
A single computer can virtualize an entire industrial site's devices, with no need to purchase physical hardware such as PLCs, cameras, or sensors; aimed at developers and testers of industrial control, gateways, host computers, and IoT platforms, solving the industry pain point of "development and debugging being blocked by hardware delivery cycles."
2026-09-03
rulego/gflow-engine
A
Embeddable approval workflow engine for Go, built on RuleGo — JSON DSL, full approval semantics, multi-tenant.
2026-09-02
mantis5x5/kvm-automation
A
Agent automation for IP-KVMs: one MCP server, CLI, fleet config, and skills driving GLKVM, PiKVM, and TinyPilot. Open-source alternative to TinyPilot Automation.
2026-08-31
bebkill/Eclipse-Cleaner
A
Clean up and stabilize a shaky solar-eclipse timelapse: drop broken frames, lock the solar disk to the center, normalize exposure.
2026-10-30
narratarr/narratarr
A
Your audiobooks: found, fetched, and playing. An *arr-style audiobook manager with a built-in player.
2026-10-26
tenhkspark/secbrief
A
A daily vulnerability briefing for AI-agent-managed machines — deterministic matching against OSV + CISA KEV; the LLM only explains. MIT
2026-10-21
PZW152/one-click-eu-lord
A
One-Click EU Lord — give Windows 11 every gain from Ireland's EU/EEA (DMA) policy without the features the EU build removes, and keep it across updates. One 166 KB exe, no runtime, fully reversible. Traditional Chinese / Simplified Chinese / English.
2026-10-21
VictorTran1023/tcl-tv-toolkit
A
China-market Android TV debugging and tuning toolbox: ADB auth, sideload, proxy, debloat, status HUD | China-market Android TV toolkit: ADB auth, sideload, proxy, debloat, status HUD
2026-10-17
Tongyi-MAI/OpenGCUA
A
An open-source stack for generalist computer-use agents, combining code execution, GUI interaction, and cross-device control.
2026-10-11
GGGODLIN/gggodlin-cc-harness
A
Governance layer of a personal Claude Code harness: gates, hooks, review and spec-to-ticket workflow. Reference, not a turnkey install.
2026-10-06
uzairansaruzi/p3-stack
B
pstack reworked for T3 Code: delegated subagents, worktree threads, PR watching, scheduled runs.
2026-09-30
silvius1996/claude-sap-kit
A
Claude Code plugin + ARC-1 extension + ABAP kit: run SAP reports, preview NAST print output as PDF, edit SmartForms as XML
2026-09-27
JoinArtisanVent/x-scraper-no-api
B
Free, self-hosted X (Twitter) scraper no API key, no credits. Uses your own browser session via Playwright. Export tweets, search results & timelines as LLM-ready JSON/CSV/Markdown. Ships an AI agent Skill for OpenClaw & Hermes.
2026-09-23
AyaseEli-Bing/Mac-Arch-Installer
A
A lazy pack for installing Arch Linux in a Mac VM | automatically installs Arch Linux ARM on Apple Silicon + Parallels Desktop (the official ISO is x86_64 only and cannot boot directly)
2026-09-10
senoff/self-hosted-ci-runner
A
Stand up self-hosted GitHub Actions runners on one box, provisioned so heavy CI jobs don't OOM or fill the disk (per-runner swap/scratch + reaper). Parameterized; Hetzner reference config included.
2026-09-09
henryzawadzki6542/cloudflare-turnstile-bypass
B
Work with Cloudflare Turnstile in Python: find the sitekey, get a valid cf-turnstile-response token in seconds. Dependency-free library + CLI, built for CI and automation.
2026-08-31
Vuk97/forward-implementation-first
B
Stop your coding agent from stalling real work on self-invented bookkeeping - receipts, hashes, locks, certification rituals. Ship first, then verify. Skill for Claude Code, Codex, and other agents.
2026-08-23
2005selene2005-a11y/susu-phone-agent
A
Android device bridge for Claude Code via MCP + Shizuku. No root, no model polling.
2026-08-23
tiammomo/RepoSteward
A
Local-first, policy-gated control plane for turning GitHub issues into verified, human-reviewed pull requests with coding agents.
2026-10-15
imhuhe/gongwen-kit
A
Official document generation and machine-check tool: generates and repairs Word official documents per GB/T 9704, and automatically checks format, numbers and writing style on output; runs locally, aimed at Party and government agencies and central state-owned enterprises
2026-09-19
indada/repopilot
B
Verification-driven AI software iteration, powered by the OpenAI Codex SDK. Self-hosted agents turn goals, GitHub Issues and PR feedback into tested, reviewable changes, with bounded execution and human control over merging and deployment.
2026-09-12
qwq77777764/catalogflow
A
Safety-first, human-approved product catalog pipeline for WooCommerce
2026-08-31
k7cfo/remove-your-data
B
Agent-first skill: remove your data from brokers without paying. Paste this URL into a coding agent.
2026-10-16
touri-ai/touri
A
touri: open-source desktop app for AI agent bots (Codex, Claude, OpenCode) with isolated VMs, browser and computer use.
2026-10-13
alibaba/qz-browser-agent
A
Local-first AI agent for Chrome: browser automation, web research, and data extraction with your own model.
2026-09-29
B0yko/booking-truth
A
Tests any AI appointment-setting agent on the calendar's end state, not its transcript: fault injection, pass^k, false-success rate. Ships a guarded Cal.com / Google Calendar / HubSpot booking agent.
2026-09-23
edison-land/paragravity
A
Native, non-invasive parallel multi-account & sandbox manager for Google Antigravity
2026-09-17
awlevin/typesafe-computer-use
B
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
2026-09-12
agent-launch/agent-launcher
A
Configure and run existing coding-agent CLIs from one desktop app.
2026-09-09
Sophomoresty/turnstile-bypass
B
Cross-platform Cloudflare Turnstile solver (macOS, Windows, Linux)
2026-09-04
codejunkie99/fable-orchestrator
B
Fable 5.1 orchestrates. GPT-5.6 Luna and DeepSeek V4 Flash implement.
2026-11-05
KKKKhazix/agent-autoloop
A
Let your command-line Agent pick up work on its own in the background and follow it through to the end; it doesn't bother you normally, and only sends a card to ask you to decide when something is uncertain.
2026-10-15
Myeongseok-Kang/claude-bulkhead
A
Keeps parallel Claude Code sessions from killing each other's servers, fighting over ports, freezing the machine, or switching a branch under each other.
2026-10-15
Thrasher2020/hyundai-pleos-europe-ha
A
Read-only Home Assistant integration for Hyundai, Kia and Genesis cars in Europe via the Pleos Vehicle Data API
2026-10-14
mylacc/yoto-audiobookshelf-bridge
A
Play your Audiobookshelf audiobooks on Yoto players, with listening progress kept in sync
2026-10-04
adityajha2005/yc-outreach
B
Pick a YC batch, get founders and likely emails, write personalised cold emails from one template. Free, stdlib Python + one HTML file, deploys on Vercel.
2026-09-21
fedorchenko-juli/job_search_tool
A
Automated job search pipeline: fetches roles from company ATS APIs and aggregators, filters and dedupes them, optionally scores fit with Claude, and reviews results in a local web board.
2026-09-17
dmtrKovalenko/bashka
B
Stop running unverified bash scripts to install software! curl <url> | bashKA for static verification of bash script safty and managing installed software
2026-09-16
missuo/wisp
A
Wisp: computer use for agents on macOS (accessibility tree + synthesized input + DevTools), with a CLI and MCP server
2026-09-08
kangleyao/slider-captcha-lab
B
Automatic Alibaba Cloud slider CAPTCHA solving: YOLO recognition + human-like trajectory generation + CDP injection, 90.9% single-attempt pass rate
2026-09-02
H0nGzA1/testpilot
A
Agentic E2E testing platform — natural-language test cases executed by a browser agent in real Chrome, judged by an LLM with video/screenshot evidence
2026-08-28
affirmitv/ghosthands
A
Give an agent real hands and eyes: undetectable, DOM-independent GUI automation. A $4 USB-HID microcontroller for hands, a vision grounding model for eyes, any LLM for a brain.
2026-08-23
ZSeven-W/dsh-android
B
DeepSeek Harness plugin for Android — build, run, and interact with a live emulator or USB device stream inside a conversation, driven entirely through adb.
2026-11-06
JosssphZhou/poki
B
Let AI agents operate a real iPhone. Local MCP server and agent, no jailbreak, no extra hardware.
2026-10-27
hieu-lee/facebook-cli
B
fb: fast, token-efficient Facebook + Messenger CLI for LLMs, driving your own logged-in Chrome
2026-10-23
xinyitang3/cftgwebproxy
B
A Telegram Web Proxy solution based on Cloudflare Pages + Worker + automatic DNS resolution. The main program runs on Pages to avoid the 1101/522 errors easily triggered by direct Worker proxying; the Worker only acts as a forwarding layer and handles preferred domains that Pages cannot route, working with automatic DNS resolution for highly available, stable access.
2026-10-11
ja1chen/actell
B
An experimental AI agent for iPhone that understands the screen and performs actions via CoreDevice, using on-device loopback or an ESP32 relay. An early-stage, vibe-coded prototype for exploration and idea sharing.
2026-10-01
OpSafari/laborix
B
Autonomous experiment-pipeline orchestrator: versioned research-plan DSL with dependency DAGs, deterministic checkpoint/resumable executor, tamper-evident provenance ledger, UCB1/Thompson schedulers with measured regret against synthetic oracles, ablation bookkeeping, offline report synthesis. NumPy core, CPU-only torch extra.
2026-09-16
wushi2333/dsh-computer-use_codex-style
B
Codex-style Computer Use for DeepSeek Harness: the official window2 13-method desktop surface plus Chromium automation, a visible overlay with Esc interrupt, per-app approvals and bundled skills. Windows, MIT, no Codex required.
2026-09-13
GreyforgeLabs/reprieve
B
A safety net for Super+W on Omarchy: the window is hidden, not terminated, and one keystroke returns it exactly as it was.
2026-09-06
byJoey/warp-masque-actions
B
GitHub Actions automatically generates Cloudflare WARP (MASQUE) keys and mihomo configs, with artifacts stored only in artifacts
2026-09-06
pierrenade/short-video-generator-AI
B
Free open-source project designed for turning youtube-viedos into viral short videos. Highlight detection, subtitles, translation, voiceover, all in one for your content.
2026-08-25
2023ai/ftmo-risk-control
B
Fail-closed FTMO risk control service and MT5/cTrader adapters for position sizing, daily loss, news windows, frequency limits, and execution audit.
2026-08-23
ripmilla/netwalk
B
Read-only network survey toolkit for AI coding agents: crawl a site from one device, diagnose it, draw it, and hand over a report — without ever changing a device or seeing a credential.
2026-11-07
devvmhq/devvm
B
One VM for every project. An isolated sandbox with your project’s toolchain, ready for you or a coding agent to start coding
2026-10-27
JunWan666/astrbot-for-android
B
Deploy and manage AstrBot and NapCat locally on an Android phone, with a built-in PRoot Ubuntu runtime, native management UI, WebUI, logs, backup and restore, and independent updates, no Root required.
2026-10-25
rddmwmddr/android-ad-cleaner
B
Turn off ads, trending searches, news recommendations, and marketing push notifications in domestic Android phone systems. No root, reversible, and supports one-click execution by AI agents.
2026-10-21
gojko/lights-on-software-factory
B
Lights-on software factory boilerplate for Claude Code. Based on the setup developed for Votito.
2026-10-21
kukemc/bili-cli
B
A Bilibili command-line tool designed for AI Agents: QR-code login, watch videos, comment, direct message, post moments, upload, all with JSON output.
2026-10-12
Liu-zhongxian/wechat-bridge
B
Official WeChat iLink bridge: bidirectional text/image/video/file sending and receiving, implemented in Python
2026-10-04
oroplex/pony
B
Pony is the hands, you pick the brain. Let Claude, Grok, Gemini or any MCP agent use your Android phone.
2026-09-23
BartolomeoRusso9/AltKeeper
B
AltServer for iOS 17+ that runs on your home server (Docker): renews and installs sideloaded iPhone apps over Wi-Fi, no computer or VPN
2026-09-10
KianSalem/headroom
B
A closed-loop agent system that mixes and masters audio toward a measured target. Orchestration graded by DSP measurement, not vibes.
2026-09-10
jankeesvw/omarchy-in-omarchy
B
A disposable Omarchy machine in QEMU/KVM that installs itself: no wizard, no disk passphrase, no login prompt
2026-09-04
WUXU-Tech/visio-com-skill
B
A clean-room Codex skill for generating editable Microsoft Visio .vsdx diagrams through local Windows COM automation.
2026-09-01
anightmonarch/codex-bridge-chatgpt
B
Verified Codex-to-ChatGPT Web reasoning handoffs with local edits, tests, and receipts.
2026-10-28
areyoubugcoder/mpider
B
Windows WeChat official account collection and offline reading workbench · native session protocol, checkpoint-based resume, Markdown / HTML export
2026-10-24
xhinzz/firered-ai-switch
B
An AI that plays Pokémon FireRed on a real Nintendo Switch: capture card in, emulated Bluetooth controller out. LLM strategist + deterministic skills, map localisation from the pret decomp, ACE toolkit.
2026-10-23
wangkaiyours/rcf-agent
B
RCF Agent: a portable Python tool for rail rolling contact fatigue, crack growth, wear and shakedown analysis with Chinese guided input and reports.
2026-10-22
huangzheng2016/ios-icon-mcp
B
Organize your iPhone home screen from any MCP-compatible AI client
2026-10-20
HorrorPills/skyrimmt
B
Skyrim SE/AE on Apple Silicon Macs: one-click setup and a native mod manager
2026-10-16
lvt1693/mashloop
B
An endless local jukebox: loops songs through seamless jump points and mixes your library into one continuous set.
2026-10-14
rorywag/Hayabusa-Bulk-Runner
B
Bulk-run Hayabusa across a folder of KAPE collections, one run per host, with per-host reports and a cross-host triage dashboard
2026-10-12
Shishir-ip/AppDNS
B
Automatically switch Android's Private DNS (DNS-over-TLS) based on the app you open. No VPN, no tracking, open source.
2026-10-08
EvilFreelancer/tgfake
B
Offline Telegram Bot API for testing bots, Mini Apps and LLM integrations.
2026-09-30
Ice-Hazymoon/jevwright
B
Browser tests for business flows, written as the steps a user takes. AI finds the controls once, recordings replay for free, and your code decides the verdict.
2026-09-26
bjarneo/flux
B
Connect an Omarchy computer to your phone: files, clipboard, notifications, media, camera, and more
2026-09-17
SakuraChanNya/QuickPPPoE
B
A lightweight, installation-free Windows PPPoE broadband dialing and auto-reconnect tool
2026-09-10
me-shaon/naming-scout
B
Names your startup, product or side project, then proves you can actually use it. Checks the domain registry, trademark, GitHub, npm, app stores and search. An agent skill for Claude Code, Cursor, Codex and 75 other agents.
2026-09-07
biusberline/cloudflare-turnstile-solver
B
A small Python library and CLI for working with Cloudflare Turnstile on your own pages - read the sitekey, build the token, verify the result.
2026-09-01
big0lives/codex-task-pointer
B
Pre-compaction hooks + a CAS-guarded task pointer that keep Codex agents on-goal across context auto-compaction — no mainline drift, no duplicate work, no conflicting progress in long runs.
2026-08-28
maybewewill/metagrid
B
Automated Dota 2 hero grids synced with the high-MMR meta in real time
2026-08-27
push-in/pam-whatsapp-web
B
A typed, persistent WhatsApp Web client for pure PHP on PAM — no Node.js or Puppeteer.
2026-08-25
dragthelake/ambient-context
B
A menu bar app that keeps a written record of what you worked on.
2026-08-24
alchaincyf/huashu-excel
B
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.
2026-11-02
lucasforster1108-boop/oracle-snatch
B
Keep asking OCI for a free-tier A1.Flex ARM instance until capacity shows up. One Python file, official API only.
2026-10-28
ere123-dev/bubbles-menu
B
Radial menu for Windows: hold a hotkey, aim at a bubble, release. File converter and screen-to-GIF built in. Радиальное меню для Windows с конвертером файлов и записью GIF.
2026-10-28
rudderlabs/devbox
B
Open source autonomous engineering harness in your cloud. One sandbox per task, no real secrets inside.
2026-10-09
agentthink/visionflow-studio
B
visionflow-studio: a low-code machine vision platform for industrial inspection. Drag and drop 110+ vision operators to build pipelines, AI assistant helps tune parameters, supports PLC and Modbus communication, and exports HDevelop and C# source code in one click.
2026-09-26
Show HN: Ekselio – Loveable for finance workflows (local first)
B
Hi everyone, I am KD - Back in my college days, I dabbled with coding, learned the basics, HTML, CSS etc. but somehow I ended up in Finance which consumed the next 20 years. Then, during covid I picked up coding again, learned react, typescript, etc - even built a rudimentary site - and then came the chatgpt moment, followed by Claude etc. So, as a side project, considering that I had spent 20 years in finance and M&A I started building Ekselio, loveable for finance workflows. Differently from other vibe coding tools, this is local first - meaning the workflows are orchestrated by the LLM based on the file schema but then the execution happens in the browser - the cool thing is that you can see the canvas, the previews of each node, and the code base (SQl) - see the Canvas tab. That said I did include a home tab, which is more of a visual, mainly because people think it's easier to relate to how folks operate, although I know finance and accounting folks usually like the workflow and full transparency - the other thing is that once you create a workflow you can save it and then next month,you can just click Run and it runs it again with no LLM tokes involved - so the infrastructure is minimal. Everything can be exported in an excel data pack with M code in case someone would want to reproduce - think Audit ready. And, I also connected to quickbooks on line so someone can directly pull in and manipulate their financials live - I also connected to Fred which carries literally 800k series in terms of macro economic data - i.e. oil prices, inflation, CPI etc and finally to stocks. I am hoping people find holes in the architecture or any ideas to make this flow a little bit better. It is in progress so if you run into bugs let me know. Considering that I am using my own API key, I have put a wall in case people overuse it but DM me if you would like to continue using, I can turn off the wall for you - hoping to keep that to a small number of users if I can and will do my best. Thank you again, appreciate you taking the time.
2026-09-24
openqa-cn/jev-browser
B
Jev Browser — indexed browser automation. Jev chooses the control, Playwright acts. A CodexQA skill.
2026-09-10
krmisystems/fantasy-football-manager
B
ESPN draft and lineup tools for Codex and other MCP clients, with browser sign-in, approval modes, per-team limits, and server monitoring.
2026-09-08
cozyblaze/portal-agent
B
The setup I used for my GPT-6 Astra Portal run: controller, SourcePauseTool patch, setup guide, and sanitized session log.
2026-09-06
pandaspa/NodePulse
B
Build multi-protocol node aggregation, subscription distribution, and a real speed-test panel with the Pterodactyl panel. The whole project has only two files, `index.js` and `package.json`, with zero third-party dependencies, and runs directly on Node.js 18+. It can also connect directly to a Telegram bot for operation
2026-09-05
bjarneo/omarchy-workspace-layout
B
Per-workspace tiling ratios for Hyprland, on Omarchy. Drag the dividers and your windows move — 25/50/25, master and stack, thirds, grid. Named layouts, per-workspace assignment, switchable profiles.
2026-09-03
slightlyuseless/pons-launch-engine
B
An open-source campaign engine for launching and sniping your own tokens on Pons
2026-08-31
moondevonyt/Trading-View-MCP-for-AI-by-Moon-Dev
B
Trading view MCP for AI so you can build anything into your trading view charts with AI
2026-08-29
KKarsyline/mac_knock
B
A very lightweight native macOS interactive popup that AI can initiate, returning your choice via HTTP or MCP.
2026-08-29
k1LoW/gh-share
B
gh-share is a GitHub CLI ( gh ) extension for sharing a single HTML file or other files and directories using GitHub Actions artifacts.
2026-08-24
mccding/NasAnySim
B
Self-hosted cellular gateway for NAS: turn a Quectel 4G module + SIM into a private phone & SMS service reachable from any browser
2026-08-23
LB623/no-negative-echo
B
Let Codex generate titles, comments, commits, and PRs based on the final result, reducing leftover rejected proposals in delivery.
2026-11-04
ef1m03/kordon
B
Kill switch for apps: freezes Claude, ChatGPT, Cursor, Telegram and other programs when the network or IP changes
2026-10-29
cutetailbud/ff-ruyijs
B
Run any site JavaScript from Python with the real Firefox engine. Headless SpiderMonkey + Necko for automation and scraping.
2026-10-24
Show HN: Making a smart TV dumb and then smart
B
GitHub anubhavmalhotra/r2d2-tv ★49 · Local home screen, private remote browser, and push-to-talk voice assistant for webOS TVs · A recent (unwanted) webOS update that got installed on TV prompted me to start going down the rabbit hole of writing new TV software. After a couple of weekends and massive help from 4 different models, finally managed to get v1 working. My daughter enjoys navigating TV through speech while I get to browse on the biggest screen at home. While all of the code was written by ML models, there were decisions I had to help with. In specific: using WebRTC to cut down latency, repurposing vendor logic for buffering voice samples and designing user experience. It was liberating to finally free the TV of bloatware and make it truly personalized!
2026-10-21
chuhe0719/QuickJump
B
Android Kotlin utility. Use Android explicit Intent to launch internal Activity of Taobao, Cainiao and Pinduoduo. One-click to open parcel identity code page. NO URL Scheme. Demo: Douyin ID:29910020595
2026-10-19
vishalsingh2972/Claude-TV
B
Remove annoying TV ads using Claude. A lightweight, ad-free home screen for Android TV & Google TV, with reversible ADB debloating.
2026-10-08
quinnovator/inhouse
B
Your own app platform on one box, with your tailnet as the front door
2026-09-28
kernel-cracker/sakura-print
B
Print and scan from phones through one home printer (Linux, CUPS, AirPrint). GPL-3.0-or-later.
2026-09-19
criterion67/drainflo
B
Local, cloud free automatic vinegar doser for an HVAC condensate drain line
2026-09-16
searchsolved/shmup-deck
B
Flyer-wall shmup launcher for MiSTer FPGA: tap a flyer on your phone, the MiSTer loads the game
2026-08-31
ih8d8/yt-dlp-manager
B
Self-hosted yt-dlp download manager: web UI, TUI and CLI over one shared queue. Single Go binary.
2026-08-24
forcewake/hermes-conductor
B
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 every incident that tried to ruin them.
2026-08-24
UsefulSoftwareCo/standardassistant
B
macOS app giving each bot its own virtual display — mirrored live and driven by forwarded input
2026-08-23
bam-bam-2/solo-skills
B
One-person entrepreneur productivity kit — automated 49 tasks without employees, and releasing 26 ready-to-use AI agent skills (+ execution scripts) among them
2026-10-26
3615nulsi/ha-awtrix-studio
B
AWTRIX 3 and AWTRIX NG (Ulanzi TC001, TC002) apps and indicators that update themselves: simple forms or Jinja templates, no automations.
2026-10-23
Juwan-Hwang/omni2api
B
Anything to API (万物皆可2API): put an AI agent, a script, or even yourself behind an OpenAI-compatible API
2026-10-21
raymondchins/Bridgeplay
C
Windows Steam games on Apple Silicon Macs, installed in one click
2026-10-15
fitzforge/polestar
B
Leveling guides for World of Warcraft: Forever: an in-game guide addon with simulated 1-60 routes, a waypoint arrow and travel planner, plus the data pipeline and authoring toolchain.
2026-10-14
cl-victor1/wechat-article-workflow-skill
B
WeChat Official Account (微信公众号) article workflow skill: topic radar → writing → cover → themed layout → drafts box
2026-10-09
Yu-ChangCheng/manufacturing-forecasting-framework
B
Reproducible monthly demand forecasting with Random Forest, chronological backtests, transparent baselines, and a guided local app.
2026-10-08
wc985732-lang/qq-live-digest
B
Real-time digest push for QQ group notifications: NapCat/OneBot v11 + AI filters out chit-chat, extracts notices and to-dos, pushes to WeChat, with a built-in mobile to-do PWA (QQ group digest with AI notice extraction and mobile task board)
2026-10-01
infinityhugo/Polymarket-Perpetual-Bot
B
Polymarket trading bot for prediction markets — browse CLOB markets, watch the order book in the terminal, run edge detection, liquidity provision and cross-market arbitrage strategies with paper trading and risk limits. Educational open-source toolkit — not financial advice. Unofficial community project, not affiliated with Polymarket.
2026-09-12
Heyosseus/sloppy
B
Laravel-aware static analysis for the code-quality patterns AI coding agents leave behind. Deterministic, local, no LLM.
2026-10-26
thecorinian/home-assistant-candlelight
B
Warm-white candlelight for Home Assistant: correlated turbulence, natural gusts, and per-bulb control.
2026-10-23
lasharor/cleanyourtv-WebOS
B
A clean home screen for rooted LG webOS TVs, with an optional debloat of LG's ads and telemetry.
2026-10-17
chegom/ig-cardnews
B
Instagram card news carousel auto-generation — an 8-image pipeline that creates backgrounds with gpt-image-2/FLUX and overlays Korean text precisely with Pillow
2026-10-16
VantaCode420/SmartHdrManager
B
Automatic Windows HDR switching for games, YouTube HDR and RTX Video HDR
2026-10-13
argofowl/FowlBrowser
B
Let your AI agents use your real Chrome, in background tabs, without getting in your way.
2026-10-10
glmn-ai/neurosquad-cli
B
nsq — run several AI coding agents in your terminal and stop babysitting them. Open-source CLI by NeuroSquad.