Multi-Agent Harness for Production AI
The Harness of Harnesses: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
My AI Stand. Realtime by day, rewriting itself by night. Summon my AI superpower.
The agent that grows with you
ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.
Kapso by Leeroo: Long-running agents that optimize AI and Data systems, and learn from every experience. #1 open-source on MLE-Bench; ALE-Bench; RelBench
SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
🔨 Kyoko is the all-in-one, fully local tool for debugging and improving your AI agents.
Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning
A tiny model that teaches itself to code better. On your laptop. No cloud. No teacher model. No human feedback.
Detail-Oriented CLIP for Fine-Grained Tasks (ICLR SSI-FM 2025)
Hermes Agent-style self-improvement for Claude Code
Self-improving LLM system using Generator-Reflector-Curator pattern for online learning from execution feedback
The local-first Agentic Knowledge OS - CLI-first, self-improving, measured. Turn intentions into traceable, auditable, reusable workflows. Runs on your machine (Ollama, Neo4j, Qdrant).
[NeurIPS 2020 Spotlight Oral] "Training Stronger Baselines for Learning to Optimize", Tianlong Chen*, Weiyi Zhang*, Jingyang Zhou, Shiyu Chang, Sijia Liu, Lisa Amini, Zhangyang Wang
Ship AI-agent artifacts, not demo theater — verifier-gated, cross-family runs that learn which model wins. TRUE recursive self-improvement: its apply loop promotes changes to its own prompts and workflows with no human approval — real measurement required, nothing reviewed first. Run on a throwaway worktree; see docs/SAFETY.md.
OpenCastor — productized open-core RCAN runtime. Gateway-as-kernel + drivers + fleet + cloud bridge + UI. Layer 4 of the OpenCastor stack. See rcan.dev/compatibility for protocol versions.
Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully yours.
No Mac Mini? No problem. HermesFace is the best free way to deploy Hermes Agent on HuggingFace Spaces — 2 vCPU, 16GB RAM, 50GB storage, always online, zero cost.
To associate your repository with the self-improving topic, visit your repo's landing page and select "manage topics."