Newest
The 20 most recently created harnesses in the catalog, youngest first.
| # | Project | Stars | Δ 7d | Δ 30d | 90d trend | Age | Lang | Last push |
|---|---|---|---|---|---|---|---|---|
| 1 | alchaincyf/huashu-motion 让你的agent一键直出商业级产品宣传片：会作曲，能指着画面改。Commercial-grade launch films by your coding agent — point at the frame to cha… | 1.1k | — | — | 2 d | JavaScript | 21h ago | |
| 2 | ZJU-OmniAI/Scene-Designer Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation | 24 | — | — | 5 d | Python | 20h ago | |
| 3 | feder-cr/git-ai Git designed for AI agents. | 2.5k | — | — | 5 d | Go | 2h ago | |
| 4 | amplifthq/opentag Legacy OpenTag source history, branches, and tags. No active development or deployment. | 0 | -1,364 | -1,381 | 1 wk | TypeScript | 5d ago | |
| 5 | yuxinlaile/McD-saver 🍟 麦麦省钱助手 —— 基于麦当劳中国官方 MCP 的省钱点餐 Agent Skill：官方 calculate-price 实时核价 + 券组合优化（预算/热量约束）+ 沉默成本体检 + 官方券/团购券/积分四渠道同… | 33 | — | — | 1 wk | Python | 31m ago | |
| 6 | openbin-ai/binny BINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one. | 182 | — | — | 1 wk | Go | 2d ago | |
| 7 | trhhubsd/ARTEX ARTEX · AI autonomous penetration testing system (multi-agent LLM, Go + Next.js) · AI 自主渗透测试系统 · 百度 agent+ 攻防挑… | 1.4k | — | — | 1 wk | Go | 1d ago | |
| 8 | liaosiliangCodeLife/harness-mate-plat 端到端智能体平台：把本机的 AI Agent 变成人人可用的 Web 产品（Vue 3 + Flask + Go WS 网关 + Docker 部署） | 23 | +2 | — | 1 wk | Python | 1d ago | |
| 9 | Canvixel-Eloweny/ai-bot-groupmate Estrella Bot · QQ 群 AI 群友机器人。把 QQ 小号接给任意 OpenAI 兼容模型（本机 / DeepSeek / 智谱 / 通义），让 AI 像群友一样插话、接梗、潜水。OneBot v11 +… | 88 | +55 | — | 2 wk | JavaScript | 19h ago | |
| 10 | Sev7eEn7/dsh-sieve dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering,… | 109 | +2 | — | 2 wk | TypeScript | 10d ago | |
| 11 | openfilm/openfilm The open source AI video agent: turns any coding agent into a video agent, with an editor to change anything i… | 1.5k | — | — | 2 wk | TypeScript | 32m ago | |
| 12 | TannerMidd/pi-pocket A durable, multiplayer, mobile-first web app for Pi agents, built on Pi Durable | 530 | +150 | — | 2 wk | TypeScript | 6h ago | |
| 13 | opensec-git/Pi-Bolt Pi, the coding agent, compiled ahead of time to native code. Starts 3× sooner than Pi on Bun and uses about a… | 376 | — | — | 2 wk | TypeScript | 3h ago | |
| 14 | openqodex/openqodex Open source code review that runs in your coding agent before you push. Scanners plus a separate AI reviewer,… | 774 | +138 | — | 2 wk | TypeScript | 4d ago | |
| 15 | Harvil1/codeAgent CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans mu… | 1.0k | +660 | — | 2 wk | Python | 6d ago | |
| 16 | wuyhong715/rikkahub-agent-pure RikkaHub Agent · Pure — an Android AI agent that survives long runs. Independent hardening pass on the rikkahu… | 53 | +12 | — | 2 wk | Kotlin | 16m ago | |
| 17 | GanyuanRan/Autoloom AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free d… | 977 | +565 | — | 2 wk | JavaScript | 1h ago | |
| 18 | feder-cr/invisible_playwright_mcp Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Fi… | 2.8k | +10 | — | 3 wk | Python | 2d ago | |
| 19 | zqc3117/Spotter Official codebase for Spotter: Let the Embodied Model Lead, and the VLM Reflect for It | 204 | +20 | — | 3 wk | Python | 8h ago | |
| 20 | Leonxlnx/cinetic Cinematic launch films and motion design from code, directed by your coding agent. | 712 | — | — | 3 wk | Python | 2d ago |
Sorted by repository creation date, so this is the freshest end of the catalog, not the most proven one. A young repo with few stars has not been through much yet.
Methodology
We find candidates through GitHub Search (agent-related topics and keywords, plus a radar for repos younger than 90 days), then snapshot every repo in the pool once a day via the GraphQL API. For new entries we rebuild star history from sampled stargazer timestamps.
Fast growing ranks by (2 × stars_7d + stars_30d) × youth_bonus. Last week counts double, and young repos get a boost so giants don't bury newcomers. The other rankings sort by stars, by repo age, and by 👍 reactions on open issues.
Exclusions:archived repositories, inactive repos (no pushes in 60 days), awesome-lists, and prompt collections. We define a “harness” as a tool or framework that orchestrates an LLM to complete tasks — tool calling, context management, agentic loops. Models themselves, API wrappers, and prompt libraries do not qualify.