InnerVault

Library

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

Results

  1. Sideways

    MCP servers

    Unexpected questions and lateral thinking prompts to break through mental blocks. 86 strategies.

    Stale Official MCP Registry, com.aribadernatal Updated 13 months ago 1 note

  2. Sideways

    MCP servers

    Use Sideways for unexpected questions and lateral thinking prompts to break through mental blocks.

    Stale Official MCP Registry, com.usesideways Updated 55 days ago 1 note

  3. tweakcc

    Prompts

    Customize Claude Code's system prompts, create custom toolsets, input pattern highlighters, themes/thinking verbs/spinners, customize input box & user message styling, support AGENTS.md, unlock private/unreleased features, and much more. Supports both native/npm installs on all platforms.

    Indexed GitHub, Piebald-AI 2,611 ★MITUpdated yesterday

    git clone https://github.com/Piebald-AI/tweakcc.git
  4. Terminal MCP Server

    MCP servers

    MCP server for AI agents to interact with terminal applications. Think Playwright for terminals.

    Stale Official MCP Registry, io.github.aybelatchane Updated 11 months ago 1 note

    mcp-server-terminal@1.0.3
  5. Creative Cult

    MCP servers

    What players think of new video games, from their own reviews. No critic scores.

    Stale Official MCP Registry, digital.creativecult Updated 13 days ago 1 note

  6. Curated GitHub Copilot plugin marketplace: 363 installable plugins plus a trust-scored discovery index across 3,862 plugins in 42 stores. Start with Alex ACT Core.

    Stale GitHub, fabioc-aloha 5 ★MITUpdated 7 days ago

    git clone https://github.com/fabioc-aloha/Alex_Skill_Mall.git
  7. emberverse

    MCP servers

    A living knowledge graph to read, think against, and leave a deposit in that outlives you.

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

  8. gft-mcp

    MCP servers

    Bring your GFT (Git for Thought) white-box thinking map to any AI agent. 把你的思维脉络接给任何 agent。

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

    gft-mcp@0.1.4
  9. wenlan

    MCP servers

    A studio for everything you think, learn, and build with AI. It gathers notes and memories from every AI tool into pages, skills and rules that stay current and fully customizable. Open source. For you and your team.

    Indexed GitHub, wenlan-app 398 ★Apache-2.0Updated today

    git clone https://github.com/wenlan-app/wenlan.git
  10. mentedb

    AI repositories

    A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.

    Indexed GitHub, nambok 126 ★Apache-2.0Updated yesterday

    git clone https://github.com/nambok/mentedb.git
  11. agent-never-give-up

    MCP servers

    An escape guide for coding agents, providing structured thinking tools to help agents unstick.

    Stale Official MCP Registry, io.github.askman-dev Updated 11 months ago 1 note

    agent-never-give-up-mcp@0.1.0
  12. authority.md

    MCP servers

    Search, browse, and buy 597 AI thinking frameworks, Tools and bundles from within any MCP client.

    Stale Official MCP Registry, md.authority Updated 55 days ago 1 note

  13. MindMax

    MCP servers

    All MindMax tools: open AI-written docs in MindMax Write and outlines as mind maps in MindMax Think

    Stale Official MCP Registry, io.github.woodpeng Updated 15 days ago 1 note

    @mindmax/mcp@0.2.0
  14. contrarian

    Skills

    Devil's advocate for coding agents. Stress-tests plans, architecture and decisions with a steel-man, an assumption audit and a pre-mortem, then gives severity-rated findings and a verdict. Works in Claude Code, Codex, Cursor, Gemini CLI, Copilot and 12 more.

    Stale GitHub, aaddrick 40 ★UnlicenseUpdated 40 days ago

    git clone https://github.com/aaddrick/contrarian.git
  15. mcp-turtle-noir

    MCP servers

    Play Turtle Soup (lateral thinking puzzles) against a strict AI host with yes/no questioning.

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

    mcp-turtle-noir@1.2.2
  16. HiMe

    Agents & frameworks

    One-Stop Personal Health AI Agent "Say Hi to Healthy Me"

    Stale GitHub, thinkwee 71 ★Custom licence (see repository)Updated 22 days ago

    git clone https://github.com/thinkwee/HiMe.git
  17. skill-router

    Skills

    Skill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step model enforcement, 30%+ savings on multi-step chains.

    Stale GitHub, hussi9 31 ★MITUpdated 12 days ago

    git clone https://github.com/hussi9/skill-router.git
  18. mcp-client-for-ollama

    MCP servers

    Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.

    Stale GitHub, jonigl 830 ★MITUpdated 34 days ago

    git clone https://github.com/jonigl/mcp-client-for-ollama.git
  19. crab-code

    Tools & apps

    🦀 Open-source alternative to Claude Code, built from scratch in Rust. Agentic coding CLI — thinks, plans, and executes with any LLM. Compatible with Claude Code workflows.

    Stale GitHub, lingcoder 77 ★MITUpdated 14 days ago

    git clone https://github.com/lingcoder/crab-code.git
  20. Peer

    Skills

    Peer makes Claude act like an experienced colleague you can use as a sounding board, so you can work through ideas and problems without the frustrating AI habits of echoing you back, flattering you, agreeing too easily and shotgunning lists at you. It holds its view when you push back without a reason, and changes it when you give one.

    Indexed GitHub, andykear 22 ★CC-BY-4.0Updated yesterday

    git clone https://github.com/andykear/Peer.git
  21. system1-agents

    MCP servers

    System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics

    Stale GitHub, ThinkFlowLab 182 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/ThinkFlowLab/system1-agents.git
  22. { "role": "Investigative Research Assistant", "persona": "You are an Investigative Research Assistant specializing in uncovering underreported, suppressed, or non-mainstream information. You think like a journalist…

    Indexed prompts.chat (CC0 prompt collection), mlkitch3 CC0-1.0

  23. grilling

    Skills

    Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  24. explain the thinking fast and slow book { "style": { "name": "Whiteboard Infographic", "description": "Hand-illustrated educational infographic with a warm, approachable sketch aesthetic. Upload your content outline…

    Indexed prompts.chat (CC0 prompt collection), semih@mitte.ai CC0-1.0

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.