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. ruflo

    MCP servers

    🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

    Indexed GitHub, ruvnet 81.8k ★MITUpdated today

    git clone https://github.com/ruvnet/ruflo.git
  2. SynapseOrch

    MCP servers

    Build and run AI agent workflows: start runs, answer what they ask, search knowledge, edit agents.

    Indexed Official MCP Registry, com.synapseorch 341 ★Updated today 1 note

  3. tunnel-client

    MCP servers

    Customer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.

    Indexed GitHub, openai 639 ★Apache-2.0Updated yesterday

    git clone https://github.com/openai/tunnel-client.git
  4. flow

    MCP servers

    Aixle Flow — orchestrate coding agents through durable, inspectable workflows.

    Stale GitHub, AixleHQ 36 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/AixleHQ/flow.git
  5. ProofSlip

    MCP servers

    Receipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects

    Stale Official MCP Registry, ai.proofslip Updated 7 months ago 2 notes

    @proofslip/mcp-server@0.2.3
  6. snapstate

    MCP servers

    Persistent state for AI agent workflows. Save, resume, and replay multi-step workflows.

    Stale Official MCP Registry, io.github.timbassler88 Updated 7 months ago 2 notes

    snapstate-sdk@1.0.2
  7. agent-gate

    MCP servers

    Fail-closed quality gate and hash-chained receipt ledger for AI agent workflows.

    Stale Official MCP Registry, io.github.Jott2121 Updated 5 months ago 1 note

    mcp-agent-gate@0.1.1
  8. ExpenseBot

    MCP servers

    Receipt ingestion, Gmail capture, expense analysis, and reviewed reports for AI-agent workflows.

    Stale Official MCP Registry, io.github.TotesMagotes Updated 5 days ago 2 notes

    @expensebot/mcp-server-auth@0.6.28
  9. cQnce MCP

    MCP servers

    Add human approval to AI agent workflows through cQnce authorization tools.

    Stale Official MCP Registry, io.github.cqnce-app Updated 49 days ago 3 notes

    @cqnce/mcp-server@0.1.3
  10. Managed Playwright cloud browsers for scalable browser automation and AI agent workflows

    Stale Official MCP Registry, com.microsoft Updated 20 days ago 1 note

  11. AgentTwin

    MCP servers

    Test AI agent workflows against service twins with injected faults. Runs locally; no source upload.

    Stale Official MCP Registry, io.github.AgentTwin Updated 9 days ago 1 note

    agenttwin@0.3.27
  12. Falcon Builder

    MCP servers

    Build, debug, and publish production AI agent workflows in Falcon Builder from any MCP client.

    Stale Official MCP Registry, dev.falconbuilder Updated 45 days ago 1 note

  13. Read-only triage for n8n, MCP, webhook, and AI agent workflow production failures.

    Stale Official MCP Registry, app.netlify.agent-rescue-desk Updated 3 months ago 1 note

  14. pmx-canvas

    MCP servers

    PMX Canvas is a shared board where you and your AI agents collect and present the data and evidence behind your work. Curate that material into context for your agent's next step, then bring the results back onto the board to review and build on. You both add and edit material on the same board, in real time. Pin context to focus input and output.

    Indexed GitHub, pskoett 31 ★MITUpdated 2 days ago

    git clone https://github.com/pskoett/pmx-canvas.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.