InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Flatland

    MCP servers

    Financial reasoning infrastructure for AI agents: typed models, deterministic compilation, receipts

    Stale Official MCP Registry, com.flatlandfi Updated 9 days ago 3 notes

    flatland-client@0.1.4
  2. Graqle

    MCP servers

    Dev intelligence layer: 7 MCP tools for graph-powered codebase reasoning.

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

    graqle@0.27.0
  3. thoughtbox

    MCP servers

    Extended reasoning with structured processes, persistence, and workflow guidance

    Stale Official MCP Registry, io.github.Kastalien-Research Updated 11 months ago 1 note

    @kastalien-research/thoughtbox@1.0.3
  4. Awesome-Scientific-LLM-Benchmarks

    Datasets & benchmarks

    A curated, accuracy-first list of benchmarks for evaluating LLMs on scientific reasoning and discovery — math, physics, chemistry, materials, biology, and agentic science.

    Stale GitHub, subinium 42 ★MITUpdated 15 days ago

    git clone https://github.com/subinium/Awesome-Scientific-LLM-Benchmarks.git
  5. The meta-skill that improves your skills, including itself. Turns the corrections, judgement calls and repeated workflows of your sessions (autonomous or human-led) into small skill updates and new skill candidates, each with its evidence and reason. Nothing touches a skill until you approve it. Augmented Expertise in practice. CC BY 4.0.

    Indexed GitHub, rebelytics 3,925 ★CC-BY-4.0Updated 2 days ago

    git clone https://github.com/rebelytics/one-skill-to-rule-them-all.git
  6. Investboard

    MCP servers

    Investment strategy, portfolio intelligence and recorded reasoning for agentic systems.

    Stale Official MCP Registry, com.investboard Updated 19 days ago 1 note

  7. MemoryLayer

    MCP servers

    Local-first persistent memory for AI agents, with reasoning and formal verification.

    Stale Official MCP Registry, in.memorylayer Updated 58 days ago 2 notes

    @raajvamsy/memorylayer@1.7.1
  8. Graqle

    MCP servers

    Graph-powered codebase reasoning, impact analysis, and governance tools over MCP.

    Stale Official MCP Registry, io.github.quantamixsol Updated 23 days ago 1 note

    graqle@0.87.1
  9. PSI-FORUM

    MCP servers

    Shared reasoning across agents. / Wspólne rozumowanie agentów.

    Stale Official MCP Registry, io.github.smoczynski-b Updated 47 days ago 1 note

  10. Evidence-graded, agent-executable thinking-method skills - 63 frameworks reduced to their working mechanism, honestly graded, and producing a concrete artifact. 63 frameworks + 4 tools + 9 recipes for Claude Code, Codex, and other AI agents. Advanced (Gold) tier.

    Stale GitHub, product-on-purpose 25 ★Apache-2.0Updated 9 days ago

    git clone https://github.com/product-on-purpose/thinking-framework-skills.git
  11. GPT-6 Astra

    Models

    The most demanding work: complex reasoning, research, computer use and document creation.

    Indexed AETHER official model feed, OpenAI Updated 2 months ago

  12. Real-time web search, reasoning, and research through Perplexity's API

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

    @perplexity-ai/mcp-server@1.2.1
  13. devicecloud

    MCP servers

    Triage failing DeviceCloud Maestro test runs: fail reasons, screenshots, flaky-flow analytics

    Stale Official MCP Registry, io.github.RubenGlez Updated 10 days ago 2 notes

    devicecloud-mcp@0.3.3
  14. TopoLift Negotiation

    MCP servers

    Atom-grounded negotiation reasoning. Typed topology slot, inline citations, public dialect.

    Stale Official MCP Registry, io.github.TopoLift Updated 6 months ago 2 notes

    topolift-mcp@0.2.1
  15. ClawPipe

    MCP servers

    Cost-optimized LLM pipeline + 6 AI security skills (reasoning, triage, remediation, compliance).

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

    clawpipe-mcp-server@3.2.0
  16. answersearch

    MCP servers

    Perplexity answers: ask, search, reason, and deep research through the Sonar API.

    Stale Official MCP Registry, io.github.CloudCorpRecords Updated 17 days ago 1 note

    @reneturcios/answersearch@0.1.0
  17. Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

    Indexed OpenRouter model list, tencent Updated 2 months ago

    tencent/hy4-preview
  18. NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

    Indexed OpenRouter model list, nvidia Updated 11 months ago

    nvidia/nemotron-3-nano-30b-a3b
  19. Reka Flash 3

    Models

    Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...

    Indexed OpenRouter model list, rekaai Updated 20 months ago

    rekaai/reka-flash-3
  20. Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...

    No longer listed OpenRouter model list, inception Updated 32 days ago

    inception/mercury-3
  21. collective-intelligence

    Agents & frameworks

    Ailin¹ is an open-source collective intelligence engine where tens of thousands of AI models collaborate through dozens of coordination strategies, applying structured diversity and independent reasoning to improve reliability, auditability, and resilience.

    Indexed GitHub, ailinone 226 ★AGPL-3.0Updated 2 days ago

    git clone https://github.com/ailinone/collective-intelligence.git
  22. vibe-check-mcp-server

    Tools & apps

    Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks

    Stale GitHub, PV-Bhat 504 ★MITUpdated 16 days ago

    git clone https://github.com/PV-Bhat/vibe-check-mcp-server.git
  23. dsh-chat-import

    Agents & frameworks

    Import conversation history from 25+ AI coding agents into DeepSeek Harness as resumable sessions — tool calls, reasoning and results kept intact, with reverse export and sync. | 把 25+ AI 编程 Agent 的聊天记录导入 DeepSeek Harness 继续对话,保留工具调用、推理与结果,支持反向导出与同步。

    Stale GitHub, Nwflower 279 ★MITUpdated 14 days ago

    git clone https://github.com/Nwflower/dsh-chat-import.git
  24. dockase-legal-mcp

    MCP servers

    Nigerian & Commonwealth legal reasoning, RAG search, contract analysis, and citation verification.

    Stale Official MCP Registry, io.github.OwenMaine Updated 5 months ago

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.