InnerVault

Library

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

Results

  1. garcon

    Agents & frameworks

    Self-hosted browser workspace to run coding agents in parallel, steer work as it runs, review diffs, and ship.

    Indexed GitHub, cfal 104 ★Custom licence (see repository)Updated today

    git clone https://github.com/cfal/garcon.git
  2. human-review

    Skills

    A /human-review skill for Claude Code: assembles one page that lets a human review a change set fast — diagram deltas, Code City, a feature video, complexity delta, and deep-linked snippets.

    Indexed GitHub, victorrentea 46 ★MITUpdated yesterday

    git clone https://github.com/victorrentea/human-review.git
  3. maw

    Skills

    Adversarial multi-agent pipeline for Claude Code and Codex CLI: planning, plan review, implementation, cross-model code review, QA. Installable skills, no runtime.

    Stale GitHub, pockerhead 6 ★MITUpdated 16 days ago

    git clone https://github.com/pockerhead/maw.git
  4. dsh-auto-review

    Agents & frameworks

    Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

    Stale GitHub, PerryLink 247 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/PerryLink/dsh-auto-review.git
  5. ripwire

    MCP servers

    The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss published. Paddle out with a map.

    Indexed GitHub, redhat-et 2,546 ★Apache-2.0Updated today

    git clone https://github.com/redhat-et/ripwire.git
  6. deliberation

    Agents & frameworks

    Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures the models' usefulness, too.

    Indexed GitHub, antonbabenko 183 ★MITUpdated 3 days ago

    git clone https://github.com/antonbabenko/deliberation.git
  7. squadra

    Skills

    Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.

    Indexed GitHub, dagoSte 1,277 ★MITUpdated 4 days ago

    git clone https://github.com/dagoSte/squadra.git
  8. agy-mcp

    MCP servers

    agy-mcp: Model Context Protocol (MCP) server for Google Antigravity CLI (agy) with async supervision and completion wakes.

    Stale GitHub, tphakala 20 ★MITUpdated 24 days ago

    git clone https://github.com/tphakala/agy-mcp.git
  9. ask-antigravity

    MCP servers

    Bridge Claude with Google's Antigravity CLI (agy) for code review and second opinions

    Stale Official MCP Registry, io.github.Lykhoyda 20 ★MITUpdated today 1 note

    @ask-llm/antigravity-mcp@0.8.1
  10. pocketto

    Skills

    A middleweight workflow for serious AI-coded features: less ceremony than BMAD, more accountability than Superpowers.

    Stale GitHub, rfxlamia 6 ★MITUpdated 16 days ago

    git clone https://github.com/rfxlamia/pocketto.git
  11. Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.

    Indexed GitHub, oliver-kriska 576 ★MITUpdated 3 days ago

    git clone https://github.com/oliver-kriska/claude-elixir-phoenix.git
  12. claude-dd

    Skills

    Portable Claude Code profile — 8-step dev loop, CLAUDE.md pre-commit gate, zero-hallucination policy. Install once, carry it to any machine.

    Stale GitHub, kopp0510 12 ★MITUpdated 17 days ago

    git clone https://github.com/kopp0510/claude-dd.git
  13. Deepcode

    Public APIs

    AI for code review

    Indexed public-apis (GitHub list)

  14. brain0

    Tools & apps

    The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.

    Indexed GitHub, Brain0-ai 289 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/Brain0-ai/brain0.git
  15. bug-hunter

    Agents & frameworks

    Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.

    Stale GitHub, codexstar69 541 ★MITUpdated 18 days ago

    git clone https://github.com/codexstar69/bug-hunter.git
  16. llm-context.py

    MCP servers

    Share code with LLMs via Model Context Protocol or clipboard. Rule-based customization enables easy switching between different tasks (like code review and documentation). Includes smart code outlining.

    Stale GitHub, cyberchitta 307 ★Apache-2.0Updated 29 days ago

    git clone https://github.com/cyberchitta/llm-context.py.git
  17. gitlab-mr-mcp

    MCP servers

    Interact seamlessly with GitLab repositories to manage merge requests and issues. Fetch details, add comments, and streamline your code review process with ease.

    Stale GitHub, kopfrechner 94 ★MITUpdated 21 days ago

    git clone https://github.com/kopfrechner/gitlab-mr-mcp.git
  18. An Orca best practice built around Matt Pocock's engineering skills. His chain stays: grill-with-docs, to-spec, to-tickets, then implement or implement-spec, closing with code-review. Orca supervises each step in its own worktree, with gates and merge. Not affiliated with or endorsed by Matt Pocock.

    Stale GitHub, whutlichao 9 ★MITUpdated 11 days ago

    git clone https://github.com/whutlichao/orchestra-auto.git
  19. kanso

    Skills

    Six Claude Code skills that keep AI-generated code tight. Audit, refactor, commit, PR, curate context.

    Stale GitHub, blakecyze 5 ★MITUpdated 11 days ago

    git clone https://github.com/blakecyze/kanso.git
  20. nexpath

    Prompts

    Local-first AI coding workflow for vibe coders, indie hackers, technical founders and product managers — catch missing tests and safety checks across Claude Code, Cursor, Windsurf, Replit, Lovable and Bolt.new.

    Stale GitHub, hi0001234d 359 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/hi0001234d/nexpath.git
  21. cc-thingz

    Skills

    Portable skills, agents, hooks, and Pi extensions for Claude Code, Codex CLI, Copilot, Cursor, Grok, and Pi.

    Stale GitHub, alexei-led 38 ★MITUpdated 24 days ago

    git clone https://github.com/alexei-led/cc-thingz.git
  22. agent-skills

    Skills

    Five SKILL.md files that give AI agents UX expertise: evaluate interfaces, detect UX smells, audit AI interfaces, check flows. For Cursor, Windsurf, Claude Code and kx

    Indexed GitHub, uxuiprinciples 31 ★Updated 3 days ago

    git clone https://github.com/uxuiprinciples/agent-skills.git
  23. Claude Code skill: run an approved implementation plan as parallel lanes of reviewed tasks

    Stale GitHub, noderaven 5 ★MITUpdated 11 days ago

    git clone https://github.com/noderaven/parallel-lanes.git
  24. pullboard

    Agents & frameworks

    Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.

    Stale GitHub, pullboard-dev 430 ★MITUpdated 19 days ago

    git clone https://github.com/pullboard-dev/pullboard.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.