72,362 visible repositories in the index
1–20 of 20 · 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 Ethereum Improvement Proposal repository
The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"
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.
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
A neovim plugin for interactively running code with the jupyter kernel. Fork of magma-nvim with improvements in image rendering, performance, and more
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
A framework for continual learning and recursive self-improvement through harness adapter evolution.
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
A Unified Framework for Efficient RSI Research
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.
LoopWAM: Closed-Loop Generalist Policy Improvement from Deployment Rollouts
HarnessMM: recursive self-improvement for harness token efficiency
Public repository for improvements to the EXTRABACON exploit
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements