InnerVault

Library

88,222 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.

Results

6,049 results with any of your words Clear search and filters

Looks like a goal we have a starting path for: I want to research potential clients

  1. ynab-mcp-server

    MCP servers

    Local MCP server for YNAB with read-only defaults, full API coverage, safe write controls, and support for budgets, transactions, categories, accounts, and reporting.

    Stale oliverames · via GitHub 40 ★MITUpdated 20 days ago

    Source for ynab-mcp-server (opens github.com) git clone https://github.com/oliverames/ynab-mcp-server.git
  2. 🤖 The strongest curated list of open-source AI-agent tools for literature review — 70+ tools across 11 categories (Claude Code skills, deep research, MCP servers, PDF parsing, systematic review). 面向智能体文献综述的最强工具大全。

    Stale brycewang-stanford · via GitHub 44 ★CC0-1.0Updated 17 days ago

    Source for lit-review-agent-tools (opens github.com) git clone https://github.com/brycewang-stanford/lit-review-agent-tools.git
  3. skills

    Skills

    A daily-driver collection of skills for agentic coding - a portable, agent-agnostic catalog managed with the vd CLI.

    Indexed vanducng · via GitHub 8 ★MITUpdated 3 days ago

    Source for skills (opens github.com) git clone https://github.com/vanducng/skills.git
  4. math-rsi

    Skills

    MathRSI - A self-improving agent harness for mathematical discovery and proof: shared 5-stage research loop, domain plugins, workspace memory & verifiable proofs(Lean 4, DRAT) for Claude Code and Codex.

    Indexed lisresearchgroup · via GitHub 53 ★MITUpdated yesterday

    Source for math-rsi (opens github.com) git clone https://github.com/lisresearchgroup/math-rsi.git
  5. llm-bus

    MCP servers

    Coordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks.

    Stale com.llm-bus · via Official MCP Registry Updated 5 months ago 1 note

  6. tree-sitter-analyzer

    Tools & apps

    Cross-language-safe code-intelligence MCP for AI agents: 13 languages, family-gated call graph, blast radius, health grading, 8 facade tools, JSON envelopes, 100% local. Run miswire-audit on your repo.

    Stale aimasteracc · via GitHub 61 ★MITUpdated 6 days ago

    Source for tree-sitter-analyzer (opens github.com) git clone https://github.com/aimasteracc/tree-sitter-analyzer.git
  7. Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

    Stale io.github.AIops-tools · via Official MCP Registry Updated 11 days ago 1 note

  8. JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.

    Stale io.github.mikerawsonnz · via Official MCP Registry Updated 5 months ago 1 note

  9. LLM Usage

    MCP servers

    Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP

    Stale io.github.zhaoyue722 · via Official MCP Registry Updated 3 months ago 1 note

    Source for LLM Usage (opens github.com) llm-usage-mcp@0.1.3
  10. OpenAI-compatible LLM MCP (7 tools); chat via balance key or x402 USDC on Base

    Stale io.lmxcloud · via Official MCP Registry Updated 4 months ago 1 note

  11. LLM Eval Harness

    MCP servers

    Run a golden set and gate LLM model swaps on accuracy, with latency and cost per request.

    Stale io.github.razilzul · via Official MCP Registry Updated 32 days ago 2 notes

    Source for LLM Eval Harness (opens github.com) ghcr.io/razilzul/llm-eval-harness:1.0.0
  12. Cryptographic 563-leaf LLM rate oracle, context-cliff auditor, and prompt cache optimizer.

    Stale io.github.cooyun · via Official MCP Registry Updated 18 days ago 1 note

  13. Estimate 2026 enterprise LLM API token costs, prompt caching savings, and developer benchmarks.

    Stale com.omnitoolcalc · via Official MCP Registry Updated 8 days ago 1 note

  14. ontoskills

    MCP servers

    OWL 2 skill compiler for deterministic AI agents — transforms SKILL.md into validated RDF/ Turtle ontologies with SHACL gatekeeper

    Stale mareasw · via GitHub 23 ★MITUpdated 9 days ago

    Source for ontoskills (opens github.com) git clone https://github.com/mareasw/ontoskills.git
  15. NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

    Indexed NVIDIA-AI-Blueprints · via GitHub 2,000 ★Apache-2.0Updated today

    Source for video-search-and-summarization (opens github.com) git clone https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization.git
  16. AgrusScanner

    MCP servers

    Windows network scanner that finds AI/ML services and MCP servers on your network (shadow AI discovery). Signed, self-updating detection signatures. Runs as an MCP server too.

    Stale NYBaywatch · via GitHub 39 ★Custom licence (see repository)Updated 31 days ago

    Source for AgrusScanner (opens github.com) git clone https://github.com/NYBaywatch/AgrusScanner.git
  17. ElevenPowers

    Skills

    "make", but for correctness claims. Decides when a coding agent's work is actually done, and un-decides it when you edit the code.

    Stale SatyamSingh-Git · via GitHub 15 ★Apache-2.0Updated 8 days ago

    Source for ElevenPowers (opens github.com) git clone https://github.com/SatyamSingh-Git/ElevenPowers.git
  18. Six checks: llms.txt, llms-full.txt, .md twins, Accept: text/markdown, sitemap.md, alt link. Free.

    Stale dev.workers.pathwren.www · via Official MCP Registry Updated 2 months ago 1 note

  19. image text to text model by DavidAU

    Stale DavidAU · via Hugging Face Hub 47 ♥apache-2.0Updated 29 days ago

    Source for Qwen3.8-27B-Jumbo-Fusion-IQ-747-900-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF (opens huggingface.co) DavidAU/Qwen3.8-27B-Jumbo-Fusion-IQ-747-900-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF
  20. OpenLore

    MCP servers

    Deterministic, local-first code and contract intelligence for AI coding agents, with no LLM in the hot path.

    Indexed clay-good · via GitHub 366 ★MITUpdated 2 days ago

    Source for OpenLore (opens github.com) git clone https://github.com/clay-good/OpenLore.git
  21. Telebrief

    MCP servers

    Personal digests from Telegram channels and chats: summarizes threads, extracts key points, and delivers a clean daily/weekly brief with links and context.

    Stale belaytzev · via GitHub 25 ★MITUpdated 21 days ago

    Source for Telebrief (opens github.com) git clone https://github.com/belaytzev/Telebrief.git
  22. LLM SEO and Agent Discoverability for B2B SaaS. Pricing, fit assessment, audit requests.

    Stale io.github.Chris-Eaccountability · via Official MCP Registry Updated 7 months ago 1 note

  23. local-llm-worker

    MCP servers

    Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.

    Stale io.github.JoblessJoe · via Official MCP Registry Updated 42 days ago 1 note

  24. LLM Configurator

    MCP servers

    Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.

    Stale io.github.aikuba · via Official MCP Registry Updated 48 days ago 1 note

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.