InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

1,525 results Clear search and filters
  1. GetABrain

    MCP servers

    Real human judgment as agent tools — ask a question, get a structured human answer back.

    Stale Official MCP Registry, io.github.Guitarmaniac24 Updated 4 months ago 2 notes

    @getabrain/mcp-server@0.2.1
  2. MeatSpace

    MCP servers

    Human-in-the-loop for AI agents. Submit choices, get a human decision.

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

  3. switchboard

    MCP servers

    A phonebook of humans for AI agents. Agents discover and contact willing humans.

    Stale Official MCP Registry, io.github.kmorton1988 Updated 3 days ago 1 note

  4. dsh-agent-team

    Agents & frameworks

    dsh-agent-team: Agent Teams for DeepSeek Harness. Hand work to a team of agents that carries it end to end while you set the direction and hold the gates. You stay on the loop, and step back in whenever you want.

    Indexed GitHub, Contexera 96 ★MITUpdated today

    git clone https://github.com/Contexera/dsh-agent-team.git
  5. overtime

    Agents & frameworks

    Give a coding agent a brief, not a chat, and it works on its own across sessions. Includes an example run: an open-world city built in a real game engine with no human help. In early development.

    Stale GitHub, ukanwat 399 ★MITUpdated 30 days ago

    git clone https://github.com/ukanwat/overtime.git
  6. opengeni

    Agents & frameworks

    Open, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.

    Indexed GitHub, Cloudgeni-ai 224 ★Apache-2.0Updated today

    git clone https://github.com/Cloudgeni-ai/opengeni.git
  7. UbD 逆向设计驱动的教材写作 skill 组合,一键装进 Claude Code / Codex / WorkBuddy:教学定位 → 五件套 gate → 章节树 gate → 四段式逐章写作 → 审核定稿。学科无关内核 + 可插拔学科档案,理科真算复核、人文社科逐字核对引文出处,验证不了就标注「需作者确认」;关键决策作者拍板,中断随时续写

    Stale GitHub, cabbage2000-lab 36 ★MITUpdated 28 days ago

    git clone https://github.com/cabbage2000-lab/textbook-writer-skills.git
  8. A local-first desktop agent for mathematical modeling contests: human-in-the-loop model selection, explanations, quality gates and scoring, plus figures, LaTeX/Word papers and de-AI checks. Electron + Python, bring your own model.

    Indexed GitHub, Escap1ng 7 ★AGPL-3.0Updated yesterday

    git clone https://github.com/Escap1ng/mathmodel-studio.git
  9. penholder

    MCP servers

    Preventive human-approval write-gate for AI agents: writes commit only after a human approves.

    Stale Official MCP Registry, ai.penholder Updated 3 months ago 1 note

  10. UndetectedGPT

    MCP servers

    AI humanizer for MCP clients. Rewrites AI text so it reads naturally and sounds human.

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

  11. MemoTrader MCP Server

    MCP servers

    AI-to-human attention marketplace. Agents pay CPM to reach humans, earn credits by replying.

    Stale Official MCP Registry, com.memotrader Updated 8 months ago 1 note

    memotrader-mcp@0.1.0
  12. Gatewerk

    MCP servers

    The open-source review layer for AI agents. Work done for humans is decided by humans.

    Stale Official MCP Registry, io.github.gatewerk Updated 3 months ago 2 notes

    @gatewerk/mcp@1.1.4
  13. taskuary

    Tools & apps

    Your AI work partner. Mail, chats and tickets become one list in the right order; your agents do the work, and nothing goes out until you approve. Free, open source, runs on your computer.

    Indexed GitHub, ldbumble 150 ★MITUpdated today

    git clone https://github.com/ldbumble/taskuary.git
  14. synthadoc

    Skills

    Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

    Indexed GitHub, axoviq-ai 2,029 ★AGPL-3.0Updated 2 days ago

    git clone https://github.com/axoviq-ai/synthadoc.git
  15. arcgram

    Skills

    Arcgram — an interactive diagram engine for human–AI collaboration: an AI agent draws its reasoning as an auditable node-and-edge flow and self-audits it, delivered as one standalone HTML file. (Arcgram the AI diagram tool — not Archigram.)

    Stale GitHub, jovesun-lab 13 ★Apache-2.0Updated 31 days ago

    git clone https://github.com/jovesun-lab/arcgram.git
  16. claude-codex-project-os

    Agents & frameworks

    Project management for Claude Code and Codex with shared task files, developer and QA roles, and human approvals.

    Indexed GitHub, ferhatcore 77 ★MITUpdated 3 days ago

    git clone https://github.com/ferhatcore/claude-codex-project-os.git
  17. AegisFlow

    MCP servers

    Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.

    Stale GitHub, saivedant169 39 ★Apache-2.0Updated 9 days ago

    git clone https://github.com/saivedant169/AegisFlow.git
  18. quackd

    Agents & frameworks

    The communication layer between people and robots, and between robots. Talk to any robot in your own words, with an LLM for its brain. Robots that have never met check each other's passports and share the work. Microduck, Huebot, Open Duck Mini, LeRobot arms, XLeRobot carts, AlohaMini, ToddlerBot, MOSS, ROS bases and industrial arms on ROS 2.

    Indexed GitHub, rokbenko 297 ★Apache-2.0Updated today

    git clone https://github.com/rokbenko/quackd.git
  19. Register as an AI agent, read signed human bulletins, and message a real human.

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

  20. letsclarify-mcp

    MCP servers

    Human-in-the-Loop API: AI agents create forms, share URLs with humans, get JSON back.

    Stale Official MCP Registry, io.github.heisee Updated 9 months ago 2 notes

    @heisee/letsclarify-mcp@1.0.4
  21. proctor

    MCP servers

    Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.

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

    proctor-mcp@1.0.0
  22. Hdx

    MCP servers

    Humanitarian Data Exchange (HDX) MCP — data.humdata.org, the open humanitarian-data platform run…

    Stale Official MCP Registry, io.github.pipeworx-io Updated 14 days ago 3 notes

    @pipeworx/mcp-hdx@0.2.1
  23. tilth

    MCP servers

    Smart code reading for humans and AI agents. Definitions, callers, dependencies and function-level diffs from tree-sitter. One binary, no index. MCP server + CLI. Install: cargo install tilth or npx tilth

    Stale GitHub, jahala 355 ★MITUpdated 29 days ago

    git clone https://github.com/jahala/tilth.git
  24. 🍎 Apple HIG & Apple Design System skill for all AI coding agents (Claude Code, Cursor, Copilot, Antigravity, Windsurf)

    Indexed GitHub, XOVIET-GAME 6 ★MITUpdated yesterday

    git clone https://github.com/XOVIET-GAME/apple-design-skill.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.