Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Awesome-Self-Evolving-Agents
SkillsA Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Self-Evolving Agents.
git clone https://github.com/XMUDeepLIT/Awesome-Self-Evolving-Agents.git -
EvoAgentX
AI repositories🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
git clone https://github.com/ANative-Lab/EvoAgentX.git -
GenericAgent
Agents & frameworksSelf-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
git clone https://github.com/lsdefine/GenericAgent.git -
Proteus
Agents & frameworksSelf-evolution for any agent harness. Plug in. Evolve. Measure.
git clone https://github.com/proteus-evolve/Proteus.git -
Yunjue-Agent
Agents & frameworksYunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks
git clone https://github.com/YunjueTech/Yunjue-Agent.git -
evolver
PromptsThe GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai
git clone https://github.com/EvoMap/evolver.git -
Raven
Agents & frameworksThe Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
git clone https://github.com/EverMind-AI/Raven.git -
MemOS
AI repositoriesSelf-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
git clone https://github.com/MemTensor/MemOS.git -
penguin-harness
AI repositories🐧 Unified and Stable RSI Platform
git clone https://github.com/Prism-Shadow/penguin-harness.git -
SkillOpt
SkillsSkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
git clone https://github.com/microsoft/SkillOpt.git -
openclaw.net
AI repositoriesSelf-hosted Enterprise and Personal AI + agent runtime in .NET (NativeAOT-friendly)
git clone https://github.com/clawdotnet/openclaw.net.git -
awesome-rsi
Docs & tutorialsA curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.
git clone https://github.com/lobehub/awesome-rsi.git -
CORAL
Agents & frameworksOpen-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
git clone https://github.com/Human-Agent-Society/CORAL.git -
agents
AI repositoriesAn Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents
git clone https://github.com/aiwaves-cn/agents.git -
agentica
Agents & frameworksOne person, a team of agents: CLI, Web, Desktop & Python SDK with multi-session collaboration, persistent memory, and self-evolving skills. 一个人,一支 Agent 团队:支持多终端协作、持久记忆与技能自进化的 AI Agent 框架。
git clone https://github.com/shibing624/agentica.git -
agentos
Agents & frameworksThe agent OS that evolves itself.
git clone https://github.com/iii-experimental/agentos.git -
GDPevo
Datasets & benchmarksA Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks
git clone https://github.com/Prism-Shadow/GDPevo.git -
Sage
Agents & frameworksAn RSI Agent Harness for running, evaluating, and evolving agents—with tools, skills, MCP, stateful execution, and multi-agent workflows.
git clone https://github.com/ZHangZHengEric/Sage.git -
Awesome-Self-Improving-Agents
AI repositoriesA curated list for Self-Improvement in Foundation Model Based Agentic Systems.
git clone https://github.com/selfimproving-agent/Awesome-Self-Improving-Agents.git -
agentdescent
Agents & frameworksGradient 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.
git clone https://github.com/ThinkFlowLab/agentdescent.git -
aser
AI repositoriesAser is a lightweight, self-assembling AI Agent frame.
git clone https://github.com/AmeNetwork/aser.git -
ScienceClaw
AI repositoriesVerifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
git clone https://github.com/beita6969/ScienceClaw.git -
semantix
Agents & frameworkssemantic agent kernel which make agent efficient and self-evolve
git clone https://github.com/Gnosil/semantix.git -
navin
SkillsOpen-source AI agents for coding, research and automation. Run locally with your models, persistent memory, multi-agent execution, skills, MCP and self-evolving.
git clone https://github.com/Navinspire-ia/navin.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.