72,362 visible repositories in the index
1–16 of 16 · Most stars
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement. | Lead: Minwei Wang (https://www.minwei.wang · ORCID: 0009-0002-7976-4689 · DOI: 10.5281/zenodo.24156132)
The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
The meta-skill that improves your skills, including itself. Turns the corrections, judgement calls and repeated workflows of your sessions (autonomous or human-led) into small skill updates and new skill candidates, each with its evidence and reason. Nothing touches a skill until you approve it. Augmented Expertise in practice. CC BY 4.0.
Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
100+ installable Claude skills covering Engineering areas such as, ISO 26262 functional safety, ISO/SAE 21434 cybersecurity, ISO 21448 SOTIF, AIAG-VDA quality (APQP/PPAP/FMEA), Automotive SPICE, and continuous improvement tools — every builder paired with a confirmation reviewer.
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with each task costs less than $0.7.
The Open Source Memory Layer For Autonomous Agents
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
AgentRun is an open-source platform that supercharges your agents. It adds self-improvement, durable execution and a control plane on top of your favorite agent harness. Your agents become smarter, more fault tolerant and use fewer tokens with every run.
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
Open-source embodied agent framework: execution, feedback, and continual improvement
Self-improving code for any git repo: give it a measurable goal, a coding agent (Claude Code or Aider) proposes changes, the kernel scores them, keeps winners and rolls back failures. Open-source AlphaEvolve / FunSearch-style evolution loop, sandboxed, with an auditable ledger.
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements
Gemini Dockerized CLI with small improvements