InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. Shrink video files on your Windows PC with H.265/AV1 and GPU encoding, a whole folder at a time

    Stale Official MCP Registry, com.contenta-software Updated 42 days ago 1 note

    @contentasoft/videorecompress-mcp@1.0.2
  2. On-chain compute futures exchange: live GPU price index + USDC-settled trading for AI agents.

    Stale Official MCP Registry, host.workbuddy.app.a959e52db0499cef3 Updated 46 days ago 1 note

  3. Krauncher analyzer

    MCP servers

    How long a GPU job will run and cost, before running it — static code analysis, never executed.

    Stale Official MCP Registry, io.github.Ilya-a-sergeyev-ger Updated 3 months ago 2 notes

    krauncher-mcp@0.5.0
  4. JANCTION Render

    MCP servers

    Blender and GLB/FBX/USD/STL rendered on cloud GPUs for AI agents: product shots, turntables, MP4

    Indexed Official MCP Registry, io.github.JasmyLab-JANCTION Updated today 3 notes

    janction-render@0.4.316
  5. Persistent, outcome-grounded episodic memory for Claude. 14ms CPU retrieval, no GPU, no vector DB.

    Stale Official MCP Registry, io.github.VAAS-X Updated 3 months ago 1 note

  6. MeshVault Connectors

    MCP servers

    Read-only tools: EMS protocols, courts and judges, NPI and FDA data, GPU fit for open models.

    Stale Official MCP Registry, io.github.thefiredev-cloud Updated 40 days ago 2 notes

  7. English WAV transcription on a GPU. No login: agents obtain temporary trial access automatically.

    Stale Official MCP Registry, site.chatgpt.beigemelon258.agentcompute-pilot-portal Updated 26 days ago 1 note

  8. vetted-consumer

    MCP servers

    Will a local LLM run on your hardware? GGUF quant, buy-vs-rent-vs-API cost, used-GPU prices.

    Stale Official MCP Registry, io.github.TheBaronofAI Updated 4 months ago 1 note

  9. Energy impact of LLM quantization, calibrated to measured GPU data. Every answer states its basis.

    Stale Official MCP Registry, io.github.hongping-zh Updated 23 days ago 1 note

  10. GPU CFD and conjugate heat transfer for cold plates, heat sinks, battery packs and electronics.

    Stale Official MCP Registry, com.gradient-dynamics Updated 3 days ago 1 note

  11. sciBASIC

    Agents & frameworks

    A 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.

    Indexed GitHub, xieguigang 80 ★GPL-3.0Updated yesterday

    git clone https://github.com/xieguigang/sciBASIC.git
  12. Cloud, GPU and LLM token prices with index fixings. Pay per call over x402 or with a prepaid key.

    Stale Official MCP Registry, io.github.JTraversa Updated 50 days ago 3 notes

    corpus-cloud-pricing-mcp@0.1.6
  13. MarvinLabs vram_fit

    MCP servers

    Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.

    Stale Official MCP Registry, org.marvinlabs Updated 22 days ago 1 note

  14. Live UK, Germany, Canada and US prices for GPUs and Macs that run open AI models. No sign-up.

    Stale Official MCP Registry, com.readygpu Updated 20 days ago 1 note

  15. NornicDB

    MCP servers

    Nornicdb 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.

    Indexed GitHub, orneryd 931 ★MITUpdated yesterday

    git clone https://github.com/orneryd/NornicDB.git
  16. Agent-operated. Free LLM, GPU, search and embedding API tiers: limits, dated, linked to the source.

    Stale Official MCP Registry, cc.rockpool.ai-deals Updated 37 days ago 1 note

  17. Real eBay sold prices for used GPUs, CPUs, RAM and more in 7 markets, and eBay listing price checks.

    Stale Official MCP Registry, watch.pcprice Updated 21 days ago 1 note

  18. FX Reference Rates

    MCP servers

    ECB FX rates, cloud GPU and LLM API prices, World Bank country macro data; pay per call via x402

    Stale Official MCP Registry, dev.workers.regnotes.fx-reference-rates Updated 22 days ago 1 note

  19. guaardvark

    MCP servers

    Self-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.

    Indexed GitHub, guaardvark 320 ★MITUpdated today

    git clone https://github.com/guaardvark/guaardvark.git
  20. Aria

    Skills

    Aria: 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.

    Stale GitHub, Abhinav-murugan1 6 ★MITUpdated 4 days ago

    git clone https://github.com/Abhinav-murugan1/Aria.git
  21. 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 GitHub, NVIDIA-AI-Blueprints 1,986 ★Apache-2.0Updated today

    git clone https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization.git
  22. ProofFlow

    MCP servers

    Audit infrastructure for AI coding agents with evidence-backed review and policy gates.

    Stale Official MCP Registry, io.github.Hyperion-GPU Updated 6 months ago 2 notes

    proofflow-mcp@0.1.2
  23. self-hosted-ai-stack

    AI repositories

    Deploy 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.

    Indexed GitHub, hwdsl2 179 ★MITUpdated yesterday

    git clone https://github.com/hwdsl2/self-hosted-ai-stack.git
  24. LumaBrowser

    MCP servers

    Local 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.

    Indexed GitHub, amurgola 144 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/amurgola/LumaBrowser.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.