self-improvement 开源项目推荐（1,005 个）

kingjulio8238 /Memary

The Open Source Memory Layer For Autonomous Agents

FriesI23 /mhabit

Open-source Flutter habit tracker with smart scoring, WebDAV sync, local-first storage, privacy-focused design, and support for Android, iOS, Windows, macOS, and Linux.

ant-research /AntOmniEvo

An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.

metauto-ai /GPTSwarm

第一个具有RL /预算优化的自我改进代理

ReflexioAI /claude-smart

将修正转换为偏好设置、项目专属技能以及Claude代码、Codex和OpenCode的共享技能。

nishantpainter /personal-kanban

NPS个人看板是一款敏捷的项目管理工具，可帮助您可视化工作、限制在制品（NPS）并精心设计和优化您的工作流程以获得最大产出。为了实现这一目标，它使用了列和卡。个人看板提供视觉线索、栏、收件箱限制、起点和终点，为您的成功奠定基础。

GeorgeClensy /Escape-Launcher

一个极简的安卓启动器，帮助你戒除手机成瘾

metauto-ai /HGM

🧬 The Huxley-Gödel Machine

ReflexioAI /reflexio

让你的经纪人自我提升。Reflexio 是一款人工智能代理自我提升工具，使您的人工智能代理能够持续从真实用户互动中学习。

simple-agent-lab /RSIHub

A research framework for principled agent self-improvement under frozen evaluators and declared mutation boundaries, recording verifiable lineage to make it reproducible and auditable.

nicosuave /memex

Search Claude Code, Codex, Pi, OpenCode, Github Copilot & Cursor transcripts. Resume sessions. Track tokens.

Createdd /Writing

📚📝 旅程笔记

EvoMap /awesome-agent-evolution

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

KaiWU5 /Awesome-AI4AI

Updated weekly — until humanity achieves AI4AI. 965 curated papers across Benchmarks, Harness Design, and Model Design — from long-horizon agents to recursive self-improvement. Citation rankings, GitHub stars, and source-verified weekly news.

dwebagents /AgentPipe

High performance multithreaded task execution and optimization engine for agents and dweb apps

ThinkFlowLab /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.

zli12321 /Vision-SR1

Reinforcement Learning of Vision Language Models with Self Visual Perception Reward

davidskeck /Annual-Reading-List

A list of things to read every year.

IAAR-Shanghai /ICSFSurvey

Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.

CIntellifusion /VideoDPO

Official Implementation of VideoDPO