Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improve coding agent performance.
| Date | Stars |
|---|---|
| 2026-07-31 | 1083 |
| 2026-08-04 | 1094 |
| 2026-08-06 | 1094 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<img src="./assets/evoskill_logo.png" alt="alt text" width="80%"/>
<br>
<h1>EvoSkill: Automated Skill Discovery for Coding Agents</h1>
</div>
<p align="center">
<a href="https://www.alphaxiv.org/abs/2603.02766"><img src="https://img.shields.io/badge/Paper-f73c6f?style=for-the-badge" alt="Paper"></a>
<a href="https://www.sentient.xyz/blog/evoskill-automated-skill-induction-from-agent-failures"><img src="https://img.shields.io/badge/Blog-f73c6f?style=for-the-badge" alt="Blog"></a>
<a href="https://sentient.xyz"><img src="https://img.shields.io/badge/Built%20by-Sentient%20Labs-f73c6f?style=for-the-badge" alt="Built by Sentient Labs"></a>
<a href="https://x.com/SentientAGI"> <img src="https://img.shields.io/badge/-SentientAGI-grey?logo=x&style=for-the-badge"/>
<a href="https://github.com/sentient-agi/EvoSkill/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-Apache 2.0-007ec6?style=for-the-badge" alt="License: Apache 2.0"></a>
</p>
<b>Turn your general AI agents into state-of-the-art specialists with a benchmark and EvoSkill, a toolkit for automatically creating and improving AI skills, compatible with Claude Code, Codex CLI, OpenCode, OpenHands, Goose, Harbor, and more.</b>
<b>EvoSkill</b> significantly extends the feedback-driven idea of <b>[GEPA](https://github.com/sentient-agi/gepa-plus)</b> from single-file optimization to complete agent evolution. Instead of only revising one prompt in place like GEPA, EvoSkill proposes multiple skill and prompt mutations jointly, evaluates new variants on held-out data, and has each iteration produce an entirely new agent program.
<p align="center">
<img src="./assets/examples.png" alt="EvoSkill Architecture" style="width: 75%;">
</p>
Install in seconds, then run `evoskill init` and `evoskill run` to supercharge any coding agent with <b>AI-created skills and prompts</b> automatically. Depending on the agent, you are free to use <b>any model provider</b> of your choice ([OpenRouter](https://openrouter.ai/models?q=g), [Anthropic](https://platform.claude.com/docs/en/about-claude/models/overview), [OpenAI](https://platform.openai.com/), [Fireworks](https://fireworks.ai/), and more) and <b>any model</b> you want (Claude, GLM, Minimax, Kimi, GPT, Gemini, Qwen, and others).
Also join us on [Discord](https://discord.gg/sentientfoundation) to discuss your experience, share suggestions, or show off your work!
## 🤖 Supported agents
<table>
<thead>
<tr>
<th>Agent</th>
<th>Support</th>
<th>Notes</th>
</tr>
</thead>
<tbody>
<tr>
<td><a href="https://www.anthropic.com/claude-code">Claude Code</a></td>
<td>✅</td>
<td></td>
</tr>
<tr>
<td><a href="https://opencode.ai/">OpenCode</a></td>
<td>✅</td>
<td>CLI v1.4.0+ required (structured output support)</td>
</tr>
<tr>
<td><a href="https://github.com/OpenHands/OpenHands">OpenHands</a></td>
<td>✅</td>
<td>No native structured output; uses fallback JSON extraction</td>
</tr>
<tr>
<td><a href="https://github.com/block/goose">Goose</a></td>
<td>✅</td>
<td>CLI v1.25.0+ required (skill discovery via summon extension)</td>
</tr>
<tr>
<td><a href="https://openai.com/index/introducing-codex/">Codex CLI</a></td>
<td>✅</td>
<td>Skill discovery via .agents/skills/ symlink</td>
</tr>
<tr>
<td><a href="https://github.com/harbor-framework/harbor">Harbor</a></td>
<td>✅</td>
<td>Containerized task benchmarks with built-in verifiers</td>
</tr>
</tbody>
</table>
## 🎨 Features
<table>
<thead>
<tr>
<th>Capability</th>
<th>Status</th>
<th>Explanation</th>
</tr>
</thead>
<tbody>
<tr>
<td><b>Evolution with a benchmark</b></td>
<td>✅</td>
<td>
Skills can be effectively improved against your own or academic benchmarks.
</td>
</tr>
<tr>
<td><b>CExcerpt of 24,008 characters
Read on GitHub
salah alzubi
173
76
26
17
9
7
5
2
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2c474d8681d98a99, desc:coding agent