self-evolution 开源项目推荐（133 个）

EvoMap /evolver

由 GEP 驱动的 AI 智能体自进化引擎。借助 Genes、Capsules 和 Events 实现可审计的进化。 | evomap.ai

PhyAgentOS /PhyAgentOS-core

PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursively self-improve through agentic workflows.

exoharness /exo

Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.

ghostwright /phantom

An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.

lobehub /awesome-rsi

A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.

agentic-in /elephant-agent

Personal-Model First Self Evolving AI Agent 🐘

XMUDeepLIT /Awesome-Self-Evolving-Agents

A Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Self-Evolving Agents.

nssmd /RoboRSI

Robot-agent harness with a CLI and local Web console for LIBERO short evaluation

summerliuuu /no-no-debug

No-No Debug — Self-evolution system for AI coding assistants. 10 minutes writing code, 2 hours debugging? This skill makes your AI remember all its bugs.

AgentToolkit /altk-evolve

Self improving agents through iterations

QuantaAlpha /EvoControl

Official implementation of Controlled Self-Evolution for Algorithmic Code Optimization

EESJGong /Graph-CAD

学习文本到CAD的层级和几何感知图表示

amazinglvxw /enso-os

The first AI plugin that speaks first. Code-enforced learning + active forgetting + PAC (Proactive Accountability Challenge). Works with Claude Code, Gemini CLI, Hermes, OpenClaw.

Shiyao-Huang /awesome-agent-evolution

开放的人工智能代理进化、自我进化代理、记忆、技能、工具、基准和代理群体系统的调查和证据地图。

T0UGH /codex-self-evolution-plugin

Use spare Codex 5.3 Spark capacity to turn sessions into memory, recall, and reusable skills.

mikhailsal /ai_lives_on_computer

An experimental framework for autonomous, self-evolving AI agents living on a server with cross-session state and persistent memory.

stellarlinkco /skills

Agent skills for long-running execution, high-recall code review, and measurable self-improvement loops.

Hashevolution /James-RAG-Evol

🔐 Replayable RAG — a local-first, auditable knowledge-reasoning platform. Graph-RAG + append-only audit log + deterministic contradiction arbitration + human-gated self-evolution. Replay any past knowledge state byte-for-byte. 100% local (Ollama). MIT.

xyva-yuangui /XyvaClaw

Self-evolving AI assistant platform with 42+ skills, 5-level model fallback, lossless context, deep Feishu/Lark integration. One-click deploy. 自我进化的 AI 助手平台，一键部署。

Xzcv-hub /Awesome-LLM-Agent-Harness

LLM Agent Harnesses: A Survey of Human-Machine Interaction, Self-Evolution, and Long-Horizon Autonomy