JavaScript · open-source evidence
JavaScript repositories using AI coding agents.
Across 5,652 cataloged JavaScript repositories, qmmit considered 455,263 commits and detected 30,679 agent-attributed commits—a 6.7% aggregate floor for this catalog slice.
Repository evidence
JavaScript projects with the most detected agent commits.
Only observations with at least 100 considered commits appear here. This orders detected evidence; it does not score project quality.
a5c-ai/babysitter
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
- Detected AI share
- 60.2%
- agent commits
- 2,473
- Commits considered
- 4,107
androoAGI/starnet
A living pixel-art station where real AI agents do real work. Local-first desktop agent harness - bring your own key, watch your crew actually run.
- Detected AI share
- 28.7%
- agent commits
- 2,311
- Commits considered
- 8,062
- Detected AI share
- 45.8%
- agent commits
- 2,019
- Commits considered
- 4,406
tractorjuice/arc-kit
The Enterprise Architecture Governance Harness — strategy, architecture, delivery, and assurance using AI coding assistants
- Detected AI share
- 83.3%
- agent commits
- 983
- Commits considered
- 1,180
- Detected AI share
- 81.3%
- agent commits
- 898
- Commits considered
- 1,104
- Detected AI share
- 25.7%
- agent commits
- 706
- Commits considered
- 2,749
ulsklyc/yuvomi
One home instead of many subscriptions. Yuvomi is a self-hosted family planner: tasks, calendar, budget, meals, shopping, health and more in one PWA on your own server or NAS. Docker, Podman, TrueNAS, Umbrel, Unraid. No tracking, MIT.
- Detected AI share
- 20.4%
- agent commits
- 693
- Commits considered
- 3,401
lowdefy/lowdefy
Build apps that AI can generate, humans can review, and teams can maintain. Config that works between code and natural language.
- Detected AI share
- 31%
- agent commits
- 686
- Commits considered
- 2,215
webbrain-one/webbrain
Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠
- Detected AI share
- 16.4%
- agent commits
- 619
- Commits considered
- 3,778
github/awesome-copilot
Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.
- Detected AI share
- 43.9%
- agent commits
- 550
- Commits considered
- 1,252
rullerzhou-afk/clawd-on-desk
A pixel desktop pet that watches Claude Code, Codex, Cursor & other AI coding agents — so you don't have to.
- Detected AI share
- 26.4%
- agent commits
- 523
- Commits considered
- 1,984
melonjs/melonJS
A modern & fully featured HTML5 game engine (2D & 3D) for JavaScript/TypeScript, with WebGL/WebGPU rendering, built-in physics, Tiled map & glTF support and WebAudio.
- Detected AI share
- 85.1%
- agent commits
- 493
- Commits considered
- 579
jason5ng32/MyIP
The best IP Toolbox. Check your IP address & geolocation, test IP for WebRTC and DNS IP leaks, run an IP quality check, browser fingerprint check, website availability check, network speed test, global latency test, MTR test, Whois search, and more.
- Detected AI share
- 50%
- agent commits
- 427
- Commits considered
- 854
stephengpope/thepopebot
The Pope Bot is an autonomous AI agent that you can configure and build to do just about anything you want, all day, everyday, 24/7.
- Detected AI share
- 32.2%
- agent commits
- 369
- Commits considered
- 1,146
Countly/countly-server
Countly is a privacy-first, AI-powered analytics and engagement platform for understanding and optimizing customer journeys across digital applications, from desktop and mobile to IoT and connected environments.
- Detected AI share
- 54%
- agent commits
- 348
- Commits considered
- 644
- Detected AI share
- 69.1%
- agent commits
- 337
- Commits considered
- 488
wekan/wekan
FLOSS kanban, built with Meteor. Official Public Support at GitHub issues only. Official Private Pre-Paid Support at https://wekan.fi/commercial-support/ only. Translation PRs to imports/i18n/data/en.i18n.json, other translations at https://app.transifex.com/wekan/wekan . No telemetry.
- Detected AI share
- 2.3%
- agent commits
- 333
- Commits considered
- 14,341
duolahypercho/codex-router
External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.
- Detected AI share
- 28.5%
- agent commits
- 327
- Commits considered
- 1,148
akiralereal/iptv
开箱即有 800+ 可稳定流畅播放频道的自托管 IPTV 直播源管理与分发系统,聚合了央视频、咪咕、央视、卫视、凤凰卫视、亚太、国际、地方台、体育赛事、抖音直播、B 站直播、斗鱼直播、虎牙直播、会场、场馆等,以及自定义抓取源和订阅,并提供 EPG 节目单与聚合功能;另外还自带 GUI 可视化管理后台,支持 Docker Compose 或 Node.js 运行,适合 NAS 与家庭服务器。
- Detected AI share
- 60.8%
- agent commits
- 313
- Commits considered
- 515
decolua/9router
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
- Detected AI share
- 27.7%
- agent commits
- 312
- Commits considered
- 1,125
- Detected AI share
- 79.7%
- agent commits
- 303
- Commits considered
- 380
origin-brain/beat-ai
不玩晦涩不搞少数派的 AI 入门圣经,从学生到工程师都能轻松掌握。涵盖神经网络到大模型、顶层设计到微观原理、工程实现到算法基础。 学完后,大家能彻底看懂为什么下一 token 预测这个看似不起眼的能力可以改变世界,也能发现原来 AI 并没有想象中那么神秘、那么高不可攀。 Let's just beat it !
- Detected AI share
- 72.4%
- agent commits
- 257
- Commits considered
- 355
SynkraAI/aiox-core
Synkra AIOS: AI-Orchestrated System for Full Stack Development - Core Framework v4.0
- Detected AI share
- 68.3%
- agent commits
- 252
- Commits considered
- 369
career-ops-hq/career-ops
Open-source AI job search agent and job finder: scan job boards, score each job 1-5 against your CV before you apply, tailor an ATS-friendly resume and cover letter, get interview prep and a job application tracker. It helps you fill in each application; you press Submit. Runs locally in your AI coding CLI (Claude Code, Codex, OpenCode and more).
- Detected AI share
- 12.5%
- agent commits
- 234
- Commits considered
- 1,873
Use this ecosystem view carefully
GitHub language classification is a repository-level snapshot, while the detector reads commit metadata. The aggregate is descriptive of this catalog slice and is not the published benchmark.