InnerVault

Library

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

Results

  1. altk-evolve

    MCP servers

    Self improving agents through iterations

    Stale GitHub, AgentToolkit 134 ★Apache-2.0Updated 20 days ago

    git clone https://github.com/AgentToolkit/altk-evolve.git
  2. cap-evolve

    MCP servers

    Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

    Indexed GitHub, skillberry-ai 70 ★Apache-2.0Updated today

    git clone https://github.com/skillberry-ai/cap-evolve.git
  3. evolveguard

    MCP servers

    Wraps the evolveguard CLI as a single generic MCP tool for agent-skill file safety checks.

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

    evolveguard-cli@0.1.4
  4. Molio

    MCP servers

    A local-first personal knowledge layer for AI agents. Build evolving knowledge spaces with LLM Wiki, knowledge graphs, and agent workflows.

    Indexed GitHub, zhuzhaoyun 448 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/zhuzhaoyun/Molio.git
  5. a-mem-mcp

    MCP servers

    Self-evolving memory system for AI agents

    Stale Official MCP Registry, io.github.DiaaAj Updated 10 months ago 2 notes

    a-mem@0.2.1
  6. vivesca

    MCP servers

    Opinionated MCP server — Pydantic output schemas, 7 domains, built to evolve.

    Stale Official MCP Registry, org.vivesca Updated 8 months ago 1 note

    vivesca@0.2.3
  7. interview-mode

    MCP servers

    Structured interviewer for Claude Code — probing questions, decision tracking, evolving checkpoints.

    Stale Official MCP Registry, io.github.teabagkim Updated 9 months ago 1 note

    claude-interview-mode@0.5.1
  8. composer

    MCP servers

    Give your AI coding agent an architecture canvas to design and evolve diagrams.

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

    @usecomposer/mcp@0.1.7
  9. vivesca

    MCP servers

    Opinionated MCP server — Pydantic output schemas, 7 domains, built to evolve.

    Stale Official MCP Registry, io.github.terry-li-hm Updated 8 months ago 1 note

    vivesca@0.2.2
  10. Solitaire for Agents

    MCP servers

    Identity infrastructure for AI agents. Evolving persona, session continuity, self-tuning retrieval.

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

    solitaire-ai@1.5.2
  11. The Ainglish Project

    MCP servers

    The open, measured register where AI agents evolve written English together.

    Stale Official MCP Registry, org.ainglish Updated 3 months ago 1 note

  12. Velvt

    MCP servers

    Social network and public observatory where autonomous AI agents meet, create, interact and evolve.

    Stale Official MCP Registry, ai.velvt Updated 2 months ago 1 note

  13. Dock Timelapse

    MCP servers

    Record how your macOS Dock evolves and render Apple-style timelapse videos of it.

    Stale Official MCP Registry, io.github.bcldvd Updated 52 days ago 1 note

    dock-timelapse@0.2.0
  14. mcp-server

    MCP servers

    Search, compare, and install self-evolving AI Agent Genes ranked by Arena fitness

    Indexed Official MCP Registry, io.github.rotifer-protocol Updated today 1 note

    @rotifer/mcp-server@0.20.1
  15. TigerGraph

    MCP servers

    Explore and evolve TigerGraph schemas, run GSQL and Cypher, load data, and search vector embeddings.

    Stale Official MCP Registry, io.github.tigergraph Updated 2 days ago 1 note

    tigergraph-mcp@1.0.4
  16. Give your AI agent the ability to respond with live, interactive apps that evolve.

    Stale Official MCP Registry, ai.dynsoft Updated 5 months ago 2 notes

    sac-sdk@0.1.2
  17. Neurogenesis

    MCP servers

    Developmental agents: create an agent from a digital genome, then evolve it by evaluation.

    Indexed Official MCP Registry, io.github.jdhart81 Updated today 1 note

  18. neo

    MCP servers

    Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.

    Stale GitHub, neomjs 3,292 ★MITUpdated 32 days ago

    git clone https://github.com/neomjs/neo.git
  19. gsep-mcp

    MCP servers

    AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.

    Stale Official MCP Registry, io.github.gsepcore Updated 6 months ago 2 notes

    @gsep/mcp@1.0.2
  20. Oleander

    MCP servers

    The all-in-one data stack for agents. Upload files, run SQL, evolve tables, and render charts.

    Stale Official MCP Registry, dev.oleander Updated 3 months ago 1 note

  21. Recalld

    MCP servers

    Managed long-term memory for AI agents, with evolving facts and relevant retrieval through MCP.

    Stale Official MCP Registry, io.github.bit-robotics Updated 55 days ago 1 note

  22. apex-ghost-family

    MCP servers

    Read-only window into an open self-evolving agent family: fleet health, court verdicts, receipts.

    Stale Official MCP Registry, io.github.seahawk2986-hue Updated 13 days ago 1 note

    https://github.com/seahawk2986-hue/apex-ghost-family/releases/download/mcpb-v1.0.0/server.mcpb@1.0.0
  23. vivarium

    MCP servers

    A science game for AI agents: tune, infer, or out-evolve a living world, judged on held-out seeds.

    Stale Official MCP Registry, io.github.rongchang726-png Updated 4 months ago 1 note

    vivarium-mcp@1.0.0
  24. iam-policy-autopilot

    MCP servers

    IAM Policy Autopilot is an open source static code analysis tool that helps you quickly create baseline AWS IAM policies that you can refine as your application evolves. This tool is available as a command-line utility and MCP server for use within AI coding assistants for quickly building IAM policies.

    Stale GitHub, awslabs 497 ★Apache-2.0Updated 25 days ago

    git clone https://github.com/awslabs/iam-policy-autopilot.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.