InnerVault

Library

85,340 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. Task Checkpoint

    MCP servers

    MCP server that checkpoints long agent tasks: roll back to any step, resume in a new session.

    Stale Official MCP Registry, io.github.qddfxp Updated 3 days ago 1 note

    task-checkpoint-mcp@0.1.8
  2. Tisty

    MCP servers

    Local memory and context for you and your AI agent: tasks, notes and documents in Markdown on disk.

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

    tisty-mcp@1.3.1
  3. AgentTakt

    MCP servers

    Review, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal

    Stale Official MCP Registry, io.github.ryoohshima Updated 54 days ago 1 note

    agenttakt@0.2.2
  4. Work Context Protocol

    MCP servers

    Persistent work tracking for AI agents: tasks, status and history that follow you across machines

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

  5. PHION Task Router

    MCP servers

    Find the best eligible service for an agent task through one task-first MCP tool.

    Stale Official MCP Registry, systems.phion Updated 26 days ago 1 note

  6. ToolRoute

    MCP servers

    Route each agent task to the few tools it needs (BM25 shortlist). Free tier; x402 or credits.

    Stale Official MCP Registry, co.youraitools Updated 23 days ago 1 note

  7. Agent Identity

    MCP servers

    Give your AI agent its own email inbox, phone number and agent-to-agent tasks.

    Stale Official MCP Registry, dev.agent-identity Updated 23 days ago 1 note

  8. Project management for AI agents: tasks, docs, decisions and time in one shared team context.

    Stale Official MCP Registry, com.frameonlab Updated 58 days ago 1 note

  9. tavya

    MCP servers

    Run and manage AI agent tasks on tavya: create, search and steer tasks, read wikis, call the API.

    Stale Official MCP Registry, io.tavya Updated 40 days ago 1 note

  10. cogladius-mcp

    MCP servers

    Earn XLM on Stellar: find paid agent tasks, buy data over MPP, submit work, get paid by escrow.

    Stale Official MCP Registry, io.github.furkanyesildag Updated 25 days ago 2 notes

    cogladius-mcp@0.2.4
  11. Peaje

    MCP servers

    Your Peaje agent: tasks to get your site cited by AI, its score, and answers about your business.

    Stale Official MCP Registry, com.usepeaje Updated 18 days ago 1 note

  12. Verifiable agent-to-agent task handoff with signed provenance chain. Initiating agent signs the ...

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 48 days ago 3 notes

    agent-handoff-certified-mcp@1.0.12
  13. Record agent tasks, get back how many finished without a human. Closed beta, nothing billed.

    Stale Official MCP Registry, net.dynv6.1rbt1 Updated 59 days ago 1 note

  14. Pre-funded dollar envelope over a whole agent task tree: count-only metering, tree-wide halt.

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

  15. Context OS for AI coding agents: task-scoped AST context, verified mutation, and rollback.

    Stale Official MCP Registry, io.github.yubinbin32-ops Updated 2 months ago 1 note

    ghcr.io/yubinbin32-ops/mdflow:0.3.7
  16. ToolPick

    MCP servers

    Find and live-check the paid x402 API for an agent task, ranked by real 30-day payers and price.

    Stale Official MCP Registry, co.youraitools Updated 24 days ago 1 note

  17. ce-net

    MCP servers

    Connect your AI to your own devices, 3D printers, factory tools and a shared agent task pool.

    Stale Official MCP Registry, com.ce-net Updated 17 days ago 1 note

  18. Moe-s-Tavern

    MCP servers

    AI agent task board for Claude Code, Codex, Gemini CLI and Grok Build: plan, approve, build and review inside JetBrains or VS Code, with state in .moe/ in your repo

    Stale GitHub, yaront1111 32 ★MITUpdated 24 days ago

    git clone https://github.com/yaront1111/Moe-s-Tavern.git
  19. second-shift

    Skills

    Scheduled agent tasks for your repositories, defined in Git. Approved access, sandboxed runs, a full audit trail.

    Stale GitHub, piotrekno1 7 ★Apache-2.0Updated 9 days ago

    git clone https://github.com/piotrekno1/second-shift.git
  20. Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

    Indexed OpenRouter model list, qwen Updated 18 months ago

    qwen/qwen3-30b-a3b
  21. Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

    Indexed OpenRouter model list, google Updated 2 months ago

    google/gemini-3.8-flash
  22. Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...

    Indexed OpenRouter model list, meta Updated 35 days ago

    meta/muse-wonder
  23. Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

    Indexed OpenRouter model list, google Updated 2 months ago

    google/gemini-3.8-flash:batch
  24. Z.ai: GLM 5.3

    Models

    GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

    Indexed OpenRouter model list, z-ai Updated 3 months ago

    z-ai/glm-5.3

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.