Multi-Agent Harness for Production AI
构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端运行 Claude Code 或 Kimi Code（双引擎，两家原生订阅直接用），共享记忆、Agent 工厂、定时任务、通信总线。
CORAL is a robust, lightweight infrastructure for multi-agent autonomous self-evolution, built for autoresearch.
Summon your AI superpower — grows with you through voice, vision, and autonomous action
SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
The agent that grows with you
Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning
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.
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)
Cognitive Memory OS for AI Agents — persistent, self-improving, multi-agent memory
Self-improving LLM system using Generator-Reflector-Curator pattern for online learning from execution feedback
[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
The bedrock layer for AI coding agents. One governance.md. Any project. Never stale. Universal skills + cross-agent compilation (Claude, Cursor, Codex, Gemini, Aider).
Open-source AI robotics framework — tiered brain, 8 AI providers, multi-robot swarm, self-improving loop
Self-improving LLM agent in TypeScript using Reflexion (verbal RL): custom evaluators, reflexion memory, HTTP API, CLI. Built with Vercel AI SDK.
Declarative Self Improving Elixir - DSPy Orchestration in Elixir
DSPEx - Declarative Self-improving Elixir | A BEAM-Native AI Program Optimization Framework
Self-improving AI: Transform CLAUDE.md into a learning system. One prompt makes Claude learn from every mistake. Meta-rules + reflection = continuous improvement.
Self-improving python code writer and error checker.
Add a description, image, and links to the self-improving topic page so that developers can more easily learn about it.
To associate your repository with the self-improving topic, visit your repo's landing page and select "manage topics."