Library
85,762 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
-
Madar
MCP serversAuthenticated local evidence paths for JavaScript and TypeScript coding agents.
@lubab/madar@0.40.0-beta.1 -
occasio
MCP serversTamper-evident, Sigstore-signed audit trail for Claude Code agents.
@occasiolabs/occasio@0.10.0 -
mindpm
MCP serversProject memory and a control plane for AI coding agents.
mindpm@3.2.0 -
football-docs
MCP serversSearchable football data provider docs for AI coding agents.
football-docs@0.2.1 -
cogmem
MCP serversA self-improving, verifiable memory layer for AI coding agents.
cogmem@2.7.1 -
Identity Forge
MCP serversDesign kits, brand naming, and domain research for coding agents.
identityforge@0.4.6 -
AgentForge
MCP serversTurn rough requests into rigorously structured prompts, for any coding agent.
agentforge-mcp@0.1.4 -
pkg
MCP serversFind, install and assemble reusable software builds for coding agents.
@tneemo/pkg@0.1.0 -
Sharphy
MCP serversCLR Intelligence and Runtime Forensic Bridge for AI Coding Agents.
Sharphy.Cli@1.1.2 -
init
MCP serversInit is the backend engineer for your coding agent.
@init-computer/mcp@0.1.8 -
ctxcap
MCP serversOffline context-budget MCP server for AI coding agents.
ctxcap-mcp@0.1.10 -
awesome-ai-built-games
Agents & frameworksA 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.
git clone https://github.com/lappemic/awesome-ai-built-games.git -
the-agency
SkillsClaude 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.
git clone https://github.com/Tekkiiiii/the-agency.git -
ai-dev-kit
SkillsAgent 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.
git clone https://github.com/AftabIbrahimKazi/ai-dev-kit.git -
vigilante
SkillsVigilante 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.
git clone https://github.com/aliengiraffe/vigilante.git -
icode-skill
SkillsAI 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。
git clone https://github.com/ayukyo/icode-skill.git -
agentgrid
SkillsSpawn grids of coding agents (Claude, Codex, Gemini, Cursor) in one command.
git clone https://github.com/naman10parikh/agentgrid.git -
CP Memory
MCP serversLocal-first, governable long-term memory for AI coding agents
cp-memory-mcp@1.8.1 -
Turnback
MCP serversUndo a coding agent turn, including shell commands and untracked files.
turnback@0.9.1 -
Sippion
MCP serversLocal read-only repository context retrieval for AI coding agents.
https://github.com/Sitten-Tokyo/Sippion/releases/download/v0.1.0/sippion-linux-x86_64.mcpb -
Subagent MCP
MCP serversLet Codex orchestrate external coding agents through their native harnesses.
subagent-harness-mcp@1.0.31 -
agentmem
MCP serversGoverned memory for coding agents. Trust lifecycle, conflict detection, health scoring.
quilmem@0.2.5 -
prinfer
MCP serversTypeScript inferred types, completions and type errors for AI coding agents
prinfer@3.4.0 -
typeprobe
MCP serversTypeScript inferred types, completions and type errors for AI coding agents
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.