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 | sagirimo/BioDSH The bioinformatics agent desktop for clinicians and wet-lab scientists — built on DeepSeek Harness. One-click… | 20 | — | — | 5 d | Python | 1d ago | |
| 2 | 555cute/r20-quantum-trader ⚡ LLM-Native Self-Evolving Quantitative Trading Terminal & Execution Engine (Bloomberg-Style Dark Terminal + 6… | 53 | — | — | 5 d | Python | 1h ago | |
| 3 | useagenthq/useagent The open-source AI coworker for your team: agents with their own cloud computer, your tools and context, handi… | 284 | — | — | 6 d | TypeScript | 3d ago | |
| 4 | XiaoDuoYa/codex-with-chatgpt ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness. | 2.4k | — | — | 1 wk | TypeScript | 26m ago | |
| 5 | hkqr/my-free-code Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming,… | 626 | — | — | 1 wk | Python | 7d ago | |
| 6 | SpatiaOS/Procedura Agentic 3D Modeling with Procedural Control — turns a text prompt into an editable parametric program, with op… | 187 | +131 | — | 1 wk | TypeScript | 8d ago | |
| 7 | UditAkhourii/cdaf CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same… | 114 | +17 | — | 1 wk | Python | 7d ago | |
| 8 | duty1g/x64dbg-mcp-server x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full… | 1.9k | +246 | — | 1 wk | Zig | 1d ago | |
| 9 | ApodexAI/FrontierAgent 🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Te… | 1.6k | +456 | — | 2 wk | Python | 6h ago | |
| 10 | sodiumsun/agenttrail An infinite canvas for your AI coding agents. Every repo is a region on one zoomable live map - watch Claude C… | 639 | — | — | 2 wk | HTML | 3d ago | |
| 11 | GamePhanesStudio/GamePhanes An open-source game coding agent environment and benchmark for Godot. | 536 | — | — | 2 wk | JavaScript | 10d ago | |
| 12 | ZSeven-W/dsh-ios DeepSeek Harness (DSH) plugin: a live iOS Simulator — and a USB-connected iPhone — inside the conversation. 22… | 275 | +12 | — | 2 wk | TypeScript | 21h ago | |
| 13 | stijnswapped/Myrqen Security testing that runs inside the coding agent you already use. Source-available, not open source. | 159 | — | — | 2 wk | TypeScript | 14d ago | |
| 14 | wang2122/sprix-sage-router Sprix AI at 屿智同行 — state-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks. | 3.4k | +991 | — | 2 wk | Python | 7d ago | |
| 15 | jermaine123123/agent-context-editor Cross-agent plugin for manually excluding and editing AI conversation context, with search, filtering, hide/re… | 54 | — | — | 2 wk | TypeScript | 4d ago | |
| 16 | Spielewoy/autoprompt-skill Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks. | 984 | +70 | — | 2 wk | JavaScript | 5d ago | |
| 17 | yancent-dao/cockpit-agent-sim Agent framework for smart-cockpit apps · 面向智能座舱业务的 Agent 框架:零后端、权限分级、确认流、卡片编排、快慢双层、真实三方集成,加能力=加数据不加代码 | 103 | +29 | — | 2 wk | TypeScript | 9d ago | |
| 18 | CopilotKit/openbot Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action… | 4.2k | +955 | — | 2 wk | TypeScript | 16h ago | |
| 19 | CopilotKit/OpenBot Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action… | 4.2k | — | — | no data | 2 wk | TypeScript | 16h ago |
| 20 | azrtydxb/procoder Senior-developer discipline for AI coding agents. A commit gate that counts unchecked as failing, quality cont… | 201 | +10 | — | 2 wk | Go | 32m 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.