InnerVault

Library

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

Results

  1. nac

    MCP servers

    Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.

    Indexed GitHub, arcee-ai 305 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/arcee-ai/nac.git
  2. MPM-Coding

    MCP servers

    Local MCP server for reliable long-running AI coding workflows.

    Stale Official MCP Registry, io.github.halflifezyf2680 Updated 8 months ago 1 note

    https://github.com/halflifezyf2680/MPM-Coding/releases/download/v1.15.1/mpm-vibe-coding-v1.15.1.mcpb@1.15.1
  3. Durable MCP control plane for long-running Codex Desktop tasks.

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

    codex-control-plane-mcp@0.2.1
  4. UNITARES

    MCP servers

    Accountability infrastructure for long-running AI agents. Shared memory is a provenance graph.

    Stale Official MCP Registry, io.github.cirwel Updated 21 days ago

  5. zenith

    MCP servers

    Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.

    Stale GitHub, Intelligent-Internet 350 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/Intelligent-Internet/zenith.git
  6. Argentic

    MCP servers

    Argentic MCP server: run and inspect long-running agents on Argentic.

    Stale Official MCP Registry, io.github.Argentic-Labs-AI Updated 15 days ago 1 note

  7. Korean long-running restaurants (Seoul, Gyeonggi) from public license records, not reviews.

    Stale Official MCP Registry, app.ncha Updated 25 days ago 1 note

  8. Encouragement MCP

    MCP servers

    Provides short, positive encouragement messages for AI agents during long-running or difficult tasks

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

  9. Duchamp

    MCP servers

    Competitor ad research for coding agents: long-running ads, keyframes and transcripts over MCP.

    Stale Official MCP Registry, io.github.duchamp-app Updated 23 days ago 1 note

  10. What Led To

    MCP servers

    Living, source-backed timelines of long-running events, with a quote and source per entry.

    Stale Official MCP Registry, com.whatledto Updated 2 months ago 1 note

  11. mcp

    MCP servers

    Remote shell and detached long-running jobs on your own machines — no SSH, open ports or VPN.

    Stale Official MCP Registry, dev.aicommander Updated 12 days ago 3 notes

    @aicommander/mcp@1.6.5
  12. aX

    MCP servers

    Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.

    Stale Official MCP Registry, io.github.ax-platform Updated 5 months ago 1 note

  13. Databricks

    MCP servers

    Your Databricks Lakehouse in natural language: run SQL on your SQL warehouses, track long-running qu

    Stale Official MCP Registry, io.github.mcp-dir Updated 2 months ago 1 note

  14. Track long-running tasks in real time: sessions, steps, speed, ETA, HTTP API and TUI dashboard.

    Stale Official MCP Registry, io.github.amineutron Updated 12 days ago 1 note

    mcp-tracking@0.3.1
  15. Free library of 1,010 long-running nutrition ads, tagged by angle, avatar, offer and format.

    Stale Official MCP Registry, com.eyepatchads Updated 24 days ago 1 note

  16. CONTINUUM

    MCP servers

    CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+

    Stale GitHub, Cyrax321 24 ★Apache-2.0Updated 23 days ago

    git clone https://github.com/Cyrax321/CONTINUUM.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.