Library
88,222 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
ynab-mcp-server
MCP serversLocal MCP server for YNAB with read-only defaults, full API coverage, safe write controls, and support for budgets, transactions, categories, accounts, and reporting.
Source for ynab-mcp-server (opens github.com) git clone https://github.com/oliverames/ynab-mcp-server.git -
lit-review-agent-tools
Skills🤖 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。
Source for lit-review-agent-tools (opens github.com) git clone https://github.com/brycewang-stanford/lit-review-agent-tools.git -
skills
SkillsA daily-driver collection of skills for agentic coding - a portable, agent-agnostic catalog managed with the vd CLI.
Source for skills (opens github.com) git clone https://github.com/vanducng/skills.git -
math-rsi
SkillsMathRSI - 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.
Source for math-rsi (opens github.com) git clone https://github.com/lisresearchgroup/math-rsi.git -
llm-bus
MCP serversCoordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks.
-
tree-sitter-analyzer
Tools & appsCross-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.
Source for tree-sitter-analyzer (opens github.com) git clone https://github.com/aimasteracc/tree-sitter-analyzer.git -
Local LLM Guard for Ollama / llama.cpp
MCP serversGoverned local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.
Source for Local LLM Guard for Ollama / llama.cpp (opens github.com) ai-guardian-aiops@0.14.1 -
authenticated-llm-agent
MCP serversJWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
-
LLM Usage
MCP serversLocal-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP
Source for LLM Usage (opens github.com) llm-usage-mcp@0.1.3 -
LMX Cloud LLM Inference
MCP serversOpenAI-compatible LLM MCP (7 tools); chat via balance key or x402 USDC on Base
-
LLM Eval Harness
MCP serversRun a golden set and gate LLM model swaps on accuracy, with latency and cost per request.
Source for LLM Eval Harness (opens github.com) ghcr.io/razilzul/llm-eval-harness:1.0.0 -
Etuki FinOps & LLM Pricing Oracle
MCP serversCryptographic 563-leaf LLM rate oracle, context-cliff auditor, and prompt cache optimizer.
-
OmniToolCalc LLM Token & Cloud FinOps Suite
MCP serversEstimate 2026 enterprise LLM API token costs, prompt caching savings, and developer benchmarks.
-
ontoskills
MCP serversOWL 2 skill compiler for deterministic AI agents — transforms SKILL.md into validated RDF/ Turtle ontologies with SHACL gatekeeper
Source for ontoskills (opens github.com) git clone https://github.com/mareasw/ontoskills.git -
video-search-and-summarization
AI repositoriesNVIDIA 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.
Source for video-search-and-summarization (opens github.com) git clone https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization.git -
AgrusScanner
MCP serversWindows 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.
Source for AgrusScanner (opens github.com) git clone https://github.com/NYBaywatch/AgrusScanner.git -
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.
Source for ElevenPowers (opens github.com) git clone https://github.com/SatyamSingh-Git/ElevenPowers.git -
Six checks: llms.txt, llms-full.txt, .md twins, Accept: text/markdown, sitemap.md, alt link. Free.
-
image text to text model by DavidAU
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 -
OpenLore
MCP serversDeterministic, local-first code and contract intelligence for AI coding agents, with no LLM in the hot path.
Source for OpenLore (opens github.com) git clone https://github.com/clay-good/OpenLore.git -
Telebrief
MCP serversPersonal digests from Telegram channels and chats: summarizes threads, extracts key points, and delivers a clean daily/weekly brief with links and context.
Source for Telebrief (opens github.com) git clone https://github.com/belaytzev/Telebrief.git -
LLM SEO MCP — Elephant Accountability
MCP serversLLM SEO and Agent Discoverability for B2B SaaS. Pricing, fit assessment, audit requests.
-
local-llm-worker
MCP serversLocal LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Source for local-llm-worker (opens github.com) local-llm-worker@0.1.4 -
LLM Configurator
MCP serversRead-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
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.