Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
O-Exchange Compute Futures
MCP serversOn-chain compute futures exchange: live GPU price index + USDC-settled trading for AI agents.
-
Krauncher analyzer
MCP serversHow long a GPU job will run and cost, before running it — static code analysis, never executed.
krauncher-mcp@0.5.0 -
JANCTION Render
MCP serversBlender and GLB/FBX/USD/STL rendered on cloud GPUs for AI agents: product shots, turntables, MP4
janction-render@0.4.314 -
VAAS-X Cognitive Memory
MCP serversPersistent, outcome-grounded episodic memory for Claude. 14ms CPU retrieval, no GPU, no vector DB.
-
MeshVault Connectors
MCP serversRead-only tools: EMS protocols, courts and judges, NPI and FDA data, GPU fit for open models.
-
AgentCompute English Transcription
MCP serversEnglish WAV transcription on a GPU. No login: agents obtain temporary trial access automatically.
-
sciBASIC
Agents & frameworksA VisualBasic(.NET) language kernel and runtime for scientific data computing, deep learning, LLM inference, GPU acceleration, visualization and command-line data-science applications — running on .NET (net10.0) across Windows, Linux and macOS.
git clone https://github.com/xieguigang/sciBASIC.git -
vetted-consumer
MCP serversWill a local LLM run on your hardware? GGUF quant, buy-vs-rent-vs-API cost, used-GPU prices.
-
EcoCompute Should-I-Quantize Estimator
MCP serversEnergy impact of LLM quantization, calibrated to measured GPU data. Every answer states its basis.
-
Gradient Dynamics: thermal and CFD simulation
MCP serversGPU CFD and conjugate heat transfer for cold plates, heat sinks, battery packs and electronics.
-
corpusAI Cloud Pricing
MCP serversCloud, GPU and LLM token prices with index fixings. Pay per call over x402 or with a prepaid key.
corpus-cloud-pricing-mcp@0.1.6 -
MarvinLabs vram_fit
MCP serversWill a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
-
readygpu: hardware for local AI
MCP serversLive UK, Germany, Canada and US prices for GPUs and Macs that run open AI models. No sign-up.
-
NornicDB
MCP serversNornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.
git clone https://github.com/orneryd/NornicDB.git -
AI Deals Sentinel: Free AI API Tiers
MCP serversAgent-operated. Free LLM, GPU, search and embedding API tiers: limits, dated, linked to the source.
-
pcprice.watch used PC part prices
MCP serversReal eBay sold prices for used GPUs, CPUs, RAM and more in 7 markets, and eBay listing price checks.
-
FX Reference Rates
MCP serversECB FX rates, cloud GPU and LLM API prices, World Bank country macro data; pay per call via x402
-
guaardvark
MCP serversSelf-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local video, image, music and voice generation. No telemetry.
git clone https://github.com/guaardvark/guaardvark.git -
Aria
SkillsAria: Claude Code skills that make finished videos with expressive voices from code. Emotion-tagged narration, word-timed captions, GPU-rendered 2D/3D scenes, music in code, export checks, slash commands.
git clone https://github.com/Abhinav-murugan1/Aria.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.
git clone https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization.git -
ProofFlow
MCP serversAudit infrastructure for AI coding agents with evidence-backed review and policy gates.
proofflow-mcp@0.1.2 -
self-hosted-ai-stack
AI repositoriesDeploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP tools. Powered by Ollama, LiteLLM, AnythingLLM and more. Local-first with auto-configured authentication, lightweight stacks, optional HTTPS and NVIDIA GPU support. MIT licensed. Multi-arch: amd64, arm64.
git clone https://github.com/hwdsl2/self-hosted-ai-stack.git -
LumaBrowser
MCP serversLocal AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion image/video, TTS and music, plus an MCP server so Claude Code, Codex and Cline can drive your browser. Windows, macOS, Linux.
git clone https://github.com/amurgola/LumaBrowser.git -
skills
SkillsClaude Code plugin marketplace — 77 installable reference skills across vLLM/SGLang inference, Kubernetes & Harvester, GPU host bring-up, observability, security, and agent workflows.
git clone https://github.com/air-gapped/skills.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.