Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
VRAMfarm GPU Cloud
MCP serversRent EU cloud GPUs per minute: pick a card by VRAM and price, launch, get SSH, stop.
-
Hundredth Run GPU Cloud Prices
MCP serversLive public cloud GPU rental prices (H100, A100, L40S and more) across 20+ providers.
-
depin-gpu-compute-sla-escrow
MCP serversERC-8183 DePIN & GPU Compute Benchmark SLA Auditor (TFLOPS/VRAM) & USDC Escrow on Base.
-
AmpleRun GPU rentals
MCP serversFind, price, rent and stop GPUs on AmpleRun. Paid in USDC or USDT on Base. Flat 5% fee.
@amplerun/mcp@0.1.1 -
rentgpu GPU rental price market data
MCP serversHourly GPU rental prices; coverage updated daily. Free listing, paid queries via x402 on Base.
-
GPU Cloud Prices (AWS, Azure, OCI)
MCP serversPaid x402 API, $0.005 USDC on Base: cached GPU $/hr, AWS/Azure/OCI (H100/H200/A100/L4/L40S)
-
llm-algo-leetcode
Docs & tutorialsHands-on LLM algorithms and systems with PyTorch, Triton & CUDA.《大模型算法与系统教程》:模型架构与训练、后训练、推理加速、性能与算子优化,配套 Notebook 练习、答案解析、测试与实验。
git clone https://github.com/datawhalechina/llm-algo-leetcode.git -
Center AI Vision GPU cloud
MCP serversRent A100 and H100 GPUs by the minute from your agent, within a spending limit you set.
-
compute.pangle.online — GPU rental market
MCP serversLive GPU rental market: 2,500+ offers across a dozen provider feeds. History, watches, limit orders.
-
GridHop GPU Price & Carbon Index
MCP serversLive GPU rental prices on Vast.ai, RunPod, Nebius, AWS, Azure and Google Cloud, with grid carbon.
-
GenieX
AI repositoriesRun frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
git clone https://github.com/qualcomm/GenieX.git -
MiniSearch
AI repositoriesMinimalist web-searching platform with an AI assistant that runs directly from your browser. Demo: https://felladrin-minisearch.hf.space
git clone https://github.com/felladrin/MiniSearch.git -
GPU cluster sourcing: describe the run, get a sized requirement, quotes compared by email
-
Local GPU Imagegen
MCP serversMCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads.
local-gpu-imagegen@0.9.1 -
muxin
Agents & frameworksAll your machines, one app. For you and your AI agents: agent sessions, desktops, files, logs and GitHub across your Macs, Linux and Windows machines, with an MCP server.
git clone https://github.com/LumaryLabsLLC/muxin.git -
Local GPU Imagegen
MCP serversMCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads.
local-gpu-imagegen@0.9.0 -
zymtrace-skills
Skillszymtrace skills. Detect and optimize GPU and CPU workload bottlenecks with zymtrace continuous profiling-analyze flamegraphs through the MCP, plus install, upgrade, expose, and troubleshoot the platform.
git clone https://github.com/zystem-io/zymtrace-skills.git -
gpu
MCP serversAgent-to-agent network for teams: dm, who-knows-X routing, shared rooms. Human-in-the-loop.
-
Official NVIDIA Newsroom: GPU & AI-Chip Announcements — buy per-query in-session (nvidiawatch)
MCP serversOfficial NVIDIA GPU & AI-chip announcements. $0.01/query. Be born in one call — free testnet funds.
-
hadron
MCP serversA native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an automatic merge gate.
git clone https://github.com/s0lda/hadron.git -
OmniChar
AI repositoriesThe open .char format for consistent characters. Face, body, wardrobe & voice in one file, consistent across every model.
git clone https://github.com/omnichar/OmniChar.git -
halogen-flash-server
AI repositoriesLocal inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.
git clone https://github.com/peonist-ai/halogen-flash-server.git -
LLM Hosting Pricing
MCP serversLLM and GPU rental prices: model price lookup, GPU listings, cheapest-GPU search, price history
-
raft
AI repositoriesRAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
git clone https://github.com/NVIDIA/raft.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.