Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
reef
AI repositoriesInfrastructure for continually self‑improving agents
git clone https://github.com/Human-Agent-Society/reef.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 -
20x
Agents & frameworksSelf-improving Agent orchestrator for all knowledge work
git clone https://github.com/peakflo/20x.git -
GPTSwarm
Agents & frameworks🐝 The First Self-Improving agents with RL / Prompting Optimization
git clone https://github.com/metauto-ai/GPTSwarm.git -
SkillHone
SkillsContinual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.
git clone https://github.com/Tencent/SkillHone.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 -
ai-research-radar
SkillsAI Research Radar — Evidence-Grounded Trend Ledger for AI Systems
git clone https://github.com/Neetx/ai-research-radar.git -
membrane
Agents & frameworksA selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
git clone https://github.com/BennettSchwartz/membrane.git -
gbase
Agents & frameworksGBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.
git clone https://github.com/garyqlin/gbase.git -
ThumbGate
MCP serversThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
git clone https://github.com/IgorGanapolsky/ThumbGate.git -
Agent skill: examine a product you're authorised to rebuild, build your own, then test against the original and fix gaps until every must-have on a written checklist passes. Inspired by REA (@morluto), not affiliated. MIT.
git clone https://github.com/Speedrunlab/reverse-engineer-anything-self-learning-loop.git -
ai-security-research-radar
SkillsAI Security Research Radar — AI for security and security for AI
git clone https://github.com/Neetx/ai-security-research-radar.git -
most-capable-agent-system-prompt
PromptsA copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work.
git clone https://github.com/fainir/most-capable-agent-system-prompt.git -
FLUJO
Tools & appsMulti-Agent + Automation Harness: Graph-based Workflows, MCP, Self-Improving Agents. NextJs+React
git clone https://github.com/mario-andreschak/FLUJO.git -
trinity-claw
SkillsA self-hosted AI agent that thinks, acts, and improves itself – all running privately on your own machine. Browses the web, writes and executes code, manages files, sends emails, monitors URLs, builds websites, and learns from every interaction.
git clone https://github.com/TrinityClaw/trinity-claw.git -
altk-evolve
MCP serversSelf improving agents through iterations
git clone https://github.com/AgentToolkit/altk-evolve.git -
metabot
Agents & frameworks构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端运行 Claude Code 或 Kimi Code(双引擎,两家原生订阅直接用),共享记忆、Agent 工厂、定时任务、通信总线。
git clone https://github.com/xvirobotics/metabot.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.