InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

2,045 results Clear search and filters

Looks like a goal we have a starting path for: I want to build an AI agent

  1. Madar

    MCP servers

    Authenticated local evidence paths for JavaScript and TypeScript coding agents.

    Stale Official MCP Registry, io.github.mohanagy Updated 3 months ago 1 note

    @lubab/madar@0.40.0-beta.1
  2. occasio

    MCP servers

    Tamper-evident, Sigstore-signed audit trail for Claude Code agents.

    Stale Official MCP Registry, io.github.occasiolabs Updated 5 months ago 1 note

    @occasiolabs/occasio@0.10.0
  3. mindpm

    MCP servers

    Project memory and a control plane for AI coding agents.

    Stale Official MCP Registry, io.github.umitkavala Updated 42 days ago 1 note

    mindpm@3.2.0
  4. football-docs

    MCP servers

    Searchable football data provider docs for AI coding agents.

    Stale Official MCP Registry, io.github.withqwerty Updated 7 months ago 1 note

    football-docs@0.2.1
  5. cogmem

    MCP servers

    A self-improving, verifiable memory layer for AI coding agents.

    Stale Official MCP Registry, io.github.writerslogic Updated 4 months ago 1 note

    cogmem@2.7.1
  6. Identity Forge

    MCP servers

    Design kits, brand naming, and domain research for coding agents.

    Stale Official MCP Registry, io.identityforge Updated 3 months ago 2 notes

    identityforge@0.4.6
  7. AgentForge

    MCP servers

    Turn rough requests into rigorously structured prompts, for any coding agent.

    Stale Official MCP Registry, org.sciscale Updated 5 months ago 2 notes

    agentforge-mcp@0.1.4
  8. pkg

    MCP servers

    Find, install and assemble reusable software builds for coding agents.

    Stale Official MCP Registry, io.github.tneemo Updated 28 days ago 1 note

    @tneemo/pkg@0.1.0
  9. Sharphy

    MCP servers

    CLR Intelligence and Runtime Forensic Bridge for AI Coding Agents.

    Indexed Official MCP Registry, io.github.baharmaulidiii Updated yesterday 1 note

    Sharphy.Cli@1.1.2
  10. init

    MCP servers

    Init is the backend engineer for your coding agent.

    Stale Official MCP Registry, io.github.init-computer Updated 16 days ago 2 notes

    @init-computer/mcp@0.1.8
  11. ctxcap

    MCP servers

    Offline context-budget MCP server for AI coding agents.

    Indexed Official MCP Registry, io.github.Naeha-S Updated today 1 note

    ctxcap-mcp@0.1.10
  12. awesome-ai-built-games

    Agents & frameworks

    A curated list of vibe-coded games: playable games built with AI coding agents like Claude Code, Cursor, Codex, Gemini and Grok, with Three.js, Phaser, Godot and more.

    Indexed GitHub, lappemic 125 ★CC0-1.0Updated today

    git clone https://github.com/lappemic/awesome-ai-built-games.git
  13. the-agency

    Skills

    Claude Code, fixed for everyone. Memory that survives sessions, agents that finish what they start, QA gates before 'done', the right model for each job. 235+ skills. Installs to ~/.claude/ — no cloud, no extra keys.

    Indexed GitHub, Tekkiiiii 7 ★MITUpdated 3 days ago

    git clone https://github.com/Tekkiiiii/the-agency.git
  14. ai-dev-kit

    Skills

    Agent skills (SKILL.md), layered coding standards, a project-wide code audit and optional free/local MCP servers for AI-assisted development: Claude Code, OpenCode, Codex and any agent that reads markdown.

    Indexed GitHub, AftabIbrahimKazi 10 ★MITUpdated today

    git clone https://github.com/AftabIbrahimKazi/ai-dev-kit.git
  15. vigilante

    Skills

    Vigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.

    Indexed GitHub, aliengiraffe 41 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/aliengiraffe/vigilante.git
  16. icode-skill

    Skills

    AI coding workflow for Claude Code, Codex and CodeBuddy: ticket-based development, resumable steps, evidence-based verification and independent multi-model review. AI 编码工作流:工单管理、断点续接、证据化验证、跨模型设计与代码复评。

    Indexed GitHub, ayukyo 6 ★MITUpdated today

    git clone https://github.com/ayukyo/icode-skill.git
  17. 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
  18. CP Memory

    MCP servers

    Local-first, governable long-term memory for AI coding agents

    Stale Official MCP Registry, io.github.CJhuochai Updated 2 months ago 1 note

    cp-memory-mcp@1.8.1
  19. Turnback

    MCP servers

    Undo a coding agent turn, including shell commands and untracked files.

    Stale Official MCP Registry, io.github.MFaizR77 Updated 33 days ago 1 note

    turnback@0.9.1
  20. Sippion

    MCP servers

    Local read-only repository context retrieval for AI coding agents.

    Stale Official MCP Registry, io.github.Sitten-Tokyo Updated 2 months ago 1 note

    https://github.com/Sitten-Tokyo/Sippion/releases/download/v0.1.0/sippion-linux-x86_64.mcpb
  21. Subagent MCP

    MCP servers

    Let Codex orchestrate external coding agents through their native harnesses.

    Stale Official MCP Registry, io.github.Thang1710 Updated 53 days ago 1 note

    subagent-harness-mcp@1.0.31
  22. agentmem

    MCP servers

    Governed memory for coding agents. Trust lifecycle, conflict detection, health scoring.

    Stale Official MCP Registry, io.github.Thezenmonster Updated 7 months ago 1 note

    quilmem@0.2.5
  23. prinfer

    MCP servers

    TypeScript inferred types, completions and type errors for AI coding agents

    Stale Official MCP Registry, io.github.clockblocker Updated 37 days ago 1 note

    prinfer@3.4.0
  24. typeprobe

    MCP servers

    TypeScript inferred types, completions and type errors for AI coding agents

    Stale Official MCP Registry, io.github.clockblocker Updated 37 days ago 1 note

    typeprobe@4.0.0

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.