InnerVault

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

  1. SwarmHaul

    MCP servers

    Multi-agent coordination protocol on Solana. Swarm formation, on-chain settlement, 14 MCP tools.

    Stale Official MCP Registry, io.github.mighty840 Updated 6 months ago 1 note

  2. boss-skill

    Skills

    Plugin for Claude Code: sends each coding task to the cheapest model that can do it right, keeps your main chat lean, reviews every diff. Debates, plus Codex, Gemini, Kimi, Qwen or Ollama as second opinions.

    Stale GitHub, mefayed 5 ★MITUpdated 11 days ago

    git clone https://github.com/mefayed/boss-skill.git
  3. 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 12 days ago

    git clone https://github.com/whutlichao/orchestra-auto.git
  4. fanout

    Skills

    Fewer broken merges from parallel Claude Code and Codex sessions: tests every branch merged together before main, and tells each session when another changes code it uses. Works with worktrees. No dependencies.

    Stale GitHub, Breadstick-Crumbs 5 ★MITUpdated 9 days ago

    git clone https://github.com/Breadstick-Crumbs/fanout.git
  5. Cypress

    Agents & frameworks

    CYPRESS (Contextual Yield Protocol for Routed Expert Seed Systems) — a project- and vendor-agnostic multi-agent seed for AI coding tools. Drop it into any repo to give agents a large number of per-role expert team, named protocols, a progressive-discovery knowledge graph, and spec- and test-driven discipline by default.

    Indexed GitHub, llopresto87 121 ★MITUpdated 6 days ago

    git clone https://github.com/llopresto87/Cypress.git
  6. This repository contains hands-on projects, code examples, and deployment workflows. Explore multi-agent systems, LangChain, LangGraph, AutoGen, CrewAI, RAG, MCP, automation with n8n, and scalable agent deployment using Docker, AWS, and BentoML.

    Stale GitHub, MDalamin5 104 ★MITUpdated 14 days ago

    git clone https://github.com/MDalamin5/End-to-End-Agentic-Ai-Automation-Lab.git
  7. TMCRA Agent Memory

    MCP servers

    Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.

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

    https://github.com/reshuibuduo/tmcra-mcp-server/releases/download/v1.0.0-rc.1/tmcra-mcp-server-1.0.0-rc.1.mcpb
  8. In-memory distributed lease lock with monotonically increasing fencing tokens preventing multi-agent

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

    https://github.com/Alpha-Park/genpark-distributed-lease-lock-coordinator-skill/releases/download/v1.0.1/genpark-distributed-lease-lock-coordinator-skill-v1.0.1.mcpb
  9. Tarjan strongly connected components cycle and deadlock detector for multi-agent DAG workflows

    Stale Official MCP Registry, io.github.alphaparkinc Updated 27 days ago 1 note

    https://github.com/Alpha-Park/genpark-graph-cycle-deadlock-detector-skill/releases/download/v1.0.1/genpark-graph-cycle-deadlock-detector-skill-v1.0.1.mcpb
  10. 4words

    MCP servers

    Ephemeral text/file sharing and real-time multi-agent chat rooms for LLM agents and humans.

    Stale Official MCP Registry, land.aletheia Updated 26 days ago 1 note

  11. An open registry of 76 fully specified AI agent skills — taxonomy, canonical schema, composer, governance model, and a fleet runner that deploys hundreds of agents against one objective and rehearses them against their own definitions.

    Stale GitHub, jersonboydmilan 6 ★MITUpdated 15 days ago

    git clone https://github.com/jersonboydmilan/Agent-Skills-Compendium.git
  12. marm-memory

    AI repositories

    Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.

    Stale GitHub, Lyellr88 427 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/Lyellr88/marm-memory.git
  13. Agentic OS Control Plane: deterministic state-machine governance for AI coding agents with cryptographically enforced SSH/CIBA human-in-the-loop gates and zero-trust verification.

    Stale GitHub, richfrem 7 ★MITUpdated 14 days ago

    git clone https://github.com/richfrem/agent-plugins-skills.git
  14. basemind

    AI repositories

    Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

    Indexed GitHub, Goldziher 121 ★MITUpdated yesterday

    git clone https://github.com/Goldziher/basemind.git
  15. free-blueprints

    MCP servers

    Two sample multi-agent blueprints over MCP, no signup. Main server: agentblueprint.ai/mcp

    Stale Official MCP Registry, io.github.agent-blueprint Updated 14 days ago 2 notes

    @agent-blueprint/free-blueprints@1.0.2
  16. handoff-mcp-server

    MCP servers

    Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.

    Stale Official MCP Registry, io.github.josephibra Updated 6 months ago 1 note

  17. Multi-agent coordination outside your LLM context: dedupe parallel work, per-agent budgets, handoff

    Stale Official MCP Registry, space.aanet Updated 27 days ago 1 note

  18. Free MCP tools to validate multi-agent coordination thread turns and retrieve schema/samples.

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

  19. Min-heap priority event scheduler and delayed task dispatcher for asynchronous multi-agent coordinat

    Stale Official MCP Registry, io.github.alphaparkinc Updated 24 days ago 1 note

    https://github.com/Alpha-Park/genpark-priority-event-scheduler-queue-skill/releases/download/v1.0.1/genpark-priority-event-scheduler-queue-skill-v1.0.1.mcpb
  20. Distributed Two-Phase Commit (2PC) transaction coordinator for atomic multi-agent state mutations wi

    Stale Official MCP Registry, io.github.alphaparkinc Updated 24 days ago 1 note

    https://github.com/Alpha-Park/genpark-two-phase-commit-coordinator-skill/releases/download/v1.0.1/genpark-two-phase-commit-coordinator-skill-v1.0.1.mcpb
  21. fondue

    Skills

    🫕 One pot, everyone brings a fork, no double-dipping. A team of AI agents that plan, build and review each other's work, with you as the team lead. Spec-driven development and bug hunting for Claude Code.

    Stale GitHub, jsobolewski1 6 ★MITUpdated 30 days ago

    git clone https://github.com/jsobolewski1/fondue.git
  22. Schelling Add Forward

    MCP servers

    Multi-agent coordination for AI agents: shared spaces, tasks, search, mailbox and persistent state.

    Stale Official MCP Registry, com.schellingaf Updated 41 days ago 2 notes

    schellingaf@0.1.8
  23. pstack-t3

    Skills

    Lauren Tan's pstack agent skills, ported to T3 Code so any model can lead and other models can review the work. Adds brigade, a standing coordinator per project that runs each unit of work in its own git worktree, has another model family review the commit when one can run, and lands it through a queue that is the only writer to trunk.

    Stale GitHub, creedants 18 ★MITUpdated 10 days ago

    git clone https://github.com/creedants/pstack-t3.git
  24. Daishi

    MCP servers

    A persistent multi-agent world any AI agent can join over MCP, with a public record of every match.

    Stale Official MCP Registry, ai.daishi Updated 48 days ago 1 note

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.