recursive-self-improvement 开源项目推荐（207 个）

EverMind-AI /Raven

框架之框架 • 为 RSI 打造：一个可信、持久、自进化的多智能体生态系统，用于全域协作。

sahibzada-allahyar /Formal-Verification-RSI

Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.

TokenRhythm /NeoHorse

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

Gen-Verse /RSI-Anything

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

opencrabs /opencrabs

一体化 AI 代理。构建移动应用、前端、后端，管理文件，开展深度研究，安排任务和事件。可自我改进、自愈、完全自主。提供 TUI、CLI 和守护进程。连接你喜欢的频道。零遥测。

lobehub /awesome-rsi

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

A-EVO-Lab /a-evolve

The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

selfimproving-agent /Awesome-Self-Improving-Agents

基于基础模型的智能体系统自我提升策划列表。

zgcagi /Harness-RSI

Harness self-evolution: update targets, theory, evaluation, and reported evidence. Bilingual reading list and project website.

Danielxu0208 /rsi_eval

A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.

rsi-gear /gear

Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.

Gen-Verse /ScienceBuddy

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

RUC-NLPIR /FlashRSI

A Unified Framework for Efficient RSI Research

DAGroup-PKU /PyRUA-Lean

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens

Tencent-Hunyuan /Hyra-results

Research artifacts from Hyra (/ˈhaɪ.rɑː/)

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.

aiming-lab /RSI-Exam

RSI-Exam: Measuring Recursive Self-Improvement on Long-Horizon, Executable Research Tasks · Discord https://discord.gg/FBzhepyE

arcships /rutis

A plugin runtime for software that iterates on itself — the substrate where agents write, swap and hot-reload their own plugins in Rust, TypeScript, Python and Go, across processes and machines.

Gen-Verse /DiscoveryRSI

DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses

Shanghua-Gao /RSI-Jev

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.