InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. paperthin

    Skills

    The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.

    Indexed GitHub, LilMGenius 1,445 ★MITUpdated yesterday

    git clone https://github.com/LilMGenius/paperthin.git
  2. darwin-skill

    Skills

    达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.

    Indexed GitHub, alchaincyf 6,935 ★MITUpdated 2 days ago

    git clone https://github.com/alchaincyf/darwin-skill.git
  3. wikimem

    Skills

    Self-improving memory for agents: ingest anything, query everything.

    Stale GitHub, naman10parikh 7 ★MITUpdated 27 days ago

    git clone https://github.com/naman10parikh/wikimem.git
  4. AI Research Radar — Evidence-Grounded Trend Ledger for AI Systems

    Indexed GitHub, Neetx 5 ★Updated today

    git clone https://github.com/Neetx/ai-research-radar.git
  5. AI Security Research Radar — AI for security and security for AI

    Indexed GitHub, Neetx 8 ★Updated today

    git clone https://github.com/Neetx/ai-security-research-radar.git
  6. honey-stack

    Skills

    Always-on workflow layer for Claude Code and Codex: right-sized tasks, smallest complete change, proof before done, plus RSI that learns from every session.

    Indexed GitHub, umararshad4 5 ★MITUpdated 2 days ago

    git clone https://github.com/umararshad4/honey-stack.git
  7. skillmaxxing

    Skills

    Self-evolving skills for your coding agent — auto-create and auto-improve skills as you work, no trigger needed.

    Stale GitHub, Bennyoooo 23 ★MITUpdated 30 days ago

    git clone https://github.com/Bennyoooo/skillmaxxing.git
  8. Self-improvement feedback loop for AI agent skills — analyzes past sessions, drafts structured improvement proposals, and gates auto-apply behind an evaluation framework. Host-agnostic (Hermes, Claude Code, and any HostAdapter).

    Stale GitHub, Carlo1911 6 ★MITUpdated 29 days ago

    git clone https://github.com/Carlo1911/skill-evolution.git
  9. TricorderKit

    Skills

    The local-first second brain for your AI agents - measured, self-improving, and gated so it can't leak what you keep private. 13 Claude Code plugins, 21 skills, Ollama, Neo4j, Qdrant.

    Stale GitHub, GeekFamilyCorp 32 ★MITUpdated 15 days ago

    git clone https://github.com/GeekFamilyCorp/TricorderKit.git
  10. SkillHone

    Skills

    Continual 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.

    Stale GitHub, Tencent 172 ★Custom licence (see repository)Updated 13 days ago

    git clone https://github.com/Tencent/SkillHone.git
  11. agentgrid

    Skills

    Spawn grids of coding agents (Claude, Codex, Gemini, Cursor) in one command.

    Stale GitHub, naman10parikh 9 ★MITUpdated 27 days ago

    git clone https://github.com/naman10parikh/agentgrid.git
  12. The self-improving context engine for coding agents.

    Stale GitHub, aerovato 503 ★BSD-3-ClauseUpdated 11 days ago

    git clone https://github.com/aerovato/operator-memory.git
  13. Continual Learning & Self-improving skills system for Claude Code - learn from corrections, never repeat mistakes

    Stale GitHub, haddock-development 382 ★Updated 10 months ago

    git clone https://github.com/haddock-development/claude-reflect-system.git
  14. Improve Claude Code and OpenAI Codex skills from real feedback, with evidence, regression checks, and human review.

    Stale GitHub, rwang23 5 ★MITUpdated 16 days ago

    git clone https://github.com/rwang23/skill-evolution.git
  15. Evidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.

    Stale GitHub, wssfk12138 12 ★MITUpdated 14 days ago

    git clone https://github.com/wssfk12138/trace-to-practice.git
  16. 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.

    Stale GitHub, Speedrunlab 23 ★MITUpdated 22 days ago

    git clone https://github.com/Speedrunlab/reverse-engineer-anything-self-learning-loop.git
  17. trinity-claw

    Skills

    A 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.

    Stale GitHub, TrinityClaw 11 ★MITUpdated 29 days ago

    git clone https://github.com/TrinityClaw/trinity-claw.git
  18. rundesk-cli

    Skills

    Persistent proactive self-improving AI teammates with memory, skills, and schedules.

    Stale GitHub, rundesk-ai 6 ★MITUpdated 25 days ago

    git clone https://github.com/rundesk-ai/rundesk-cli.git
  19. synthadoc

    Skills

    Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

    Indexed GitHub, axoviq-ai 2,029 ★AGPL-3.0Updated 2 days ago

    git clone https://github.com/axoviq-ai/synthadoc.git
  20. 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.

    Indexed GitHub, PromptPotter 7 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/PromptPotter/prompt-potter-optimizer.git
  21. recall

    Skills

    A self-improving memory layer for Claude Code: captures every session, distills them nightly into a versioned knowledge vault, and surfaces that knowledge back into new sessions — plus proposes skills from recurring patterns.

    Stale GitHub, maxdmyers 18 ★Updated 28 days ago

    git clone https://github.com/maxdmyers/recall.git
  22. A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

    Indexed GitHub, Sanexxxx777 16 ★MITUpdated today

    git clone https://github.com/Sanexxxx777/curated-claude-code.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.