InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.

    Stale GitHub, BayramAnnakov 1,801 ★MITUpdated 44 days ago

    git clone https://github.com/BayramAnnakov/claude-reflect.git
  2. A Claude Code self learning plugin that autonomously researches any technology and generates reusable SKILL.md files with installation guides, code examples, and best practices.

    Indexed GitHub, ychampion 9 ★Updated 3 days ago

    git clone https://github.com/ychampion/claude-self-learning.git
  3. 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
  4. 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
  5. vibecosystem

    Skills

    Profile-based coding runtime for Claude Code and Codex. Lean core; opt-in quality, context, memory, orchestration and dashboard.

    Stale GitHub, vibeeval 546 ★MITUpdated 5 days ago

    git clone https://github.com/vibeeval/vibecosystem.git
  6. autoharness

    Skills

    Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.

    Stale GitHub, tigerless-labs 11.1k ★MITUpdated 33 days ago

    git clone https://github.com/tigerless-labs/autoharness.git
  7. A lightweight agents and skills set to handle any kind of task! Designed to create a professional workflow with dynamic team assembly of specialized agents tailored to each task, parallel execution, optimized context windows, and a self-learning cycle.

    Stale GitHub, wcgomes 10 ★Updated 23 days ago

    git clone https://github.com/wcgomes/agents-workspace.git
  8. sno-station

    Skills

    When Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer.

    Indexed GitHub, sno-ai 1,020 ★Apache-2.0Updated today

    git clone https://github.com/sno-ai/sno-station.git
  9. Sno Station Skills: 39 tested skills that turn Claude Code and Codex into one working team. Review by a different agent, automatic handoff when an agent hits its usage limit, a one-page morning brief, work orders with proof, and a nightly loop that learns from your own sessions. Open source, installed with one sno setup.

    Indexed GitHub, sno-ai 865 ★Apache-2.0Updated today

    git clone https://github.com/sno-ai/sno-station-skills.git
  10. Holix

    Skills

    Helix is a powerful self-learning AI agent with memory, skills, and the ability to recall tools. It learns from successful tasks and creates reusable skills for the future.

    Stale GitHub, javded-itres 19 ★MITUpdated 22 days ago

    git clone https://github.com/javded-itres/Holix.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.