self-improvement
AntOmniEvo
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
- 1.2k
- Python
- Apache-2.0
- 5 d ago
claude-smart
Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
- 796
- Python
- Apache-2.0
- 1 d ago
reflexio
Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.
- 389
- Python
- Apache-2.0
- 1 d ago
memex
Search Claude Code, Codex, Pi, OpenCode, Github Copilot & Cursor transcripts. Resume sessions. Track tokens.
- 318
- Rust
- MIT
- 6 d ago
awesome-agent-evolution
A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai
- 243
- JavaScript
- 6 d ago
agentdescent
Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.
- 221
- Python
- MIT
- 2 d ago
Vision-SR1
Reinforcement Learning of Vision Language Models with Self Visual Perception Reward
- 186
- Python
- Apache-2.0
- 8 mo ago
HowToAvoidScams
人间防骗指南:373 篇骗局拆解,覆盖刷单、杀猪盘、AI 换脸、养老诈骗等 16 类;附真实案例报道、生活自查清单、PDF/EPUB/Anki 下载,还有 12 局防骗小游戏
- 153
- HTML
- 10 d ago
mentor
mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insights-style HTML report on how you work: what you build, where you lose time, and concrete fixes. An agent skill for Claude Code, Codex, and any skills-capable agent.
- 86
- Python
- MIT
- 4 mo ago
awesome-agent-evolution
Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.
- 70
- JavaScript
- MIT
- 4 mo ago
pi-reflect
Self-improving behavioral files for AI coding agents. Analyzes session transcripts for correction patterns and makes surgical edits to prevent recurrence.
- 56
- TypeScript
- MIT
- 6 wk ago
self-improving-agent-notebook
Master self-improving LLM agents systematically with runnable Stanford CS329A notebooks.
- 62
- Jupyter Notebook
- 7 wk ago
FMT-exocortex-template
Exocortex template: fork & deploy your AI-powered personal knowledge system with Claude Code
- 64
- Shell
- MIT
- 2 d ago
better-life
高性价比人生指南:650 条建议,34 个主题。省钱、避坑、少走弯路。场景导航、章节阅读、全文检索、关系图、收藏、PDF 与 Obsidian 下载。
- 46
- JavaScript
- MIT
- 6 wk ago
Skill-RSI
Skill RSI is a recursive self-improvement loop for Agent Skills, grounded in evals. Standalone or Codex plugin.
- 26
- JavaScript
- 8 wk ago
Spark
An official implementation of "SPARK: Synergistic Policy And Reward Co-Evolving Framework"
- 25
- Python
- Apache-2.0
- 13 mo ago
existence-trace
A self-improving personal state system: an AI agent reads your journal through PAD emotion, security/hope (G) and growth (XP) lenses, asks for your feedback, and turns it into rules. Python stdlib only.
- 23
- Python
- MIT
- 1 d ago
personagent
An agent that behaves like a person, on every platform you use: it has a character of its own, remembers, learns from the people it talks to, and judges for itself when to speak.
- 23
- Python
- Apache-2.0
- 8 h ago
Tsuzuku
A private, offline-first Android habit tracker, focus timer, and minimal launcher built with Kotlin, Jetpack Compose, Material 3, Room, and DataStore.
- 20
- Kotlin
- MIT
- 4 mo ago
skills
Learn from Experience skill 是让 Agent 从经验中学习 -- 纠正过的错误不再重犯,好的方法自动沉淀,越用越懂你。原理是基于你跟Agent交互中的经验(踩坑、纠正、好方法)记下来、整理好、用起来,不再随会话结束而消失。
- 20
- Shell
- 4 mo ago
rondo
Agent skills for long-horizon work: turn goals into verified results, and lessons into better runs.
- 12
- HTML
- 4 wk ago
prompt-potter-optimizer
LLM-driven evolution of prompts and pipelines. Evolves the prompt and the pipeline's parameters together against your labeled data, cuts losing candidates early, and shows every measurement behind the winner. Open source.
- 7
- Python
- 1 d ago
evolver-cursor-plugin
Official Evolver plugin for Cursor — self-evolving agent memory: recall what worked, detect improvement signals, record outcomes (session hooks + skill). MIT.
- 5
- JavaScript
- MIT
- 4 wk ago
mindX
I am mindX — a self-building cognitive architecture
Runs in the browser on Hugging Face
- 1
- apache-2.0
- 6 wk ago
ARGUS — Self-Improvement Env
A polygraph for self-improving AI · OpenEnv 2026
Runs in the browser on Hugging Face
- 1
- apache-2.0
- 7 mo ago




















