InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Evidence-driven CUDA, CUTLASS, Triton and GPU workload optimization for ChatGPT · 使用 ChatGPT 驱动 GPU workload 性能优化

    Stale GitHub, troycheng 7 ★MITUpdated 12 days ago

    git clone https://github.com/troycheng/cuda-kernel-optimizer.git
  2. GPUI Agentation

    MCP servers

    Read and manage development annotations from a local GPUI app.

    Stale Official MCP Registry, io.github.emmanuel-defreitas Updated 22 days ago 1 note

    gpui-agentation@0.6.0
  3. Run GPU acceptance tests on your NVIDIA GPU nodes over SSH: DCGM, GEMM, HBM/PCIe bandwidth, NCCL.

    Stale Official MCP Registry, com.liquidcompute Updated 32 days ago 1 note

  4. CoreHu GPU Cloud

    MCP servers

    Find, price and rent cloud GPUs for AI jobs, get GPU recommendations and manage CoreHu machines.

    Indexed Official MCP Registry, com.corehu Updated 2 days ago 1 note

  5. GPU MCP Server

    MCP servers

    NVIDIA GPU metrics as MCP tools — utilization, memory, temperature, power. Supports MIG.

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

    ghcr.io/pmady/gpu-mcp-server:v0.1.0
  6. paneflow

    MCP servers

    Native terminal multiplexer for coding agents. Persistent sessions, Git worktrees, diffs, and an integrated editor. Built with Rust and GPUI.

    Indexed GitHub, arthjean 96 ★GPL-3.0Updated yesterday

    git clone https://github.com/arthjean/paneflow.git
  7. kineo

    Agents & frameworks

    🎬 端到端 AI 漫剧 / 动画短剧 Multi-Agent 多智能体协作创作平台 (Kineo AI)。基于 Hub-and-Spoke 智能体架构、ProjectBlackboard 共享黑板、自定义 Agent 扩展插件、角色 Consistency 锚定与 4K GPU 压制。

    Indexed GitHub, Agions 135 ★MITUpdated today

    git clone https://github.com/Agions/kineo.git
  8. gpu-bridge

    MCP servers

    30 GPU-powered AI services as MCP tools. LLM, image, video, audio, embeddings & more.

    Stale Official MCP Registry, io.github.fjnunezp75 Updated 8 months ago 2 notes

    @gpu-bridge/mcp-server@2.4.3
  9. GPU Cloud

    MCP servers

    Rent H100, RTX PRO 6000, A100, L40 and RTX A6000 GPUs by the hour in Montréal, Canada, in CAD.

    Stale Official MCP Registry, ca.gpucloud Updated 37 days ago 1 note

  10. cydonia

    Tools & apps

    Agent control panel for Claude Code, Codex, OpenCode, Pi and 40+ agents with articles and boards supported

    Indexed GitHub, crabtalk 199 ★MITUpdated 2 days ago

    git clone https://github.com/crabtalk/cydonia.git
  11. gpusmarket

    MCP servers

    Rent real GPUs from the terminal. Per-second billing, $0.50 minimum. stdio MCP server.

    Stale Official MCP Registry, io.github.jyswee Updated 3 months ago 3 notes

    gpusmarket@2.4.16
  12. Metal GPU Trace

    MCP servers

    Measure Wine and macOS programs' GPU use on Apple silicon with Metal System Trace

    Indexed Official MCP Registry, io.github.partprogramming09 Updated today 1 note

    metal-gpu-trace@0.27.1
  13. Tachyon GPU monitor

    MCP servers

    Read-only NVIDIA GPU monitor: bottlenecks, VRAM forecast, crash diagnosis, pre-render check, jobs.

    Stale Official MCP Registry, io.github.formray Updated 18 days ago 1 note

    https://github.com/formray/tachyon/releases/download/v1.2.0/tachyon-1.2.0-windows-x64.mcpb@1.2.0
  14. GPUvec

    MCP servers

    Compare GPU specs and cloud rental offers, check CUDA support, and estimate Qdrant resources.

    Stale Official MCP Registry, io.github.abdelkareemkobo Updated 15 days ago 1 note

  15. pegainfer

    AI repositories

    Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

    Stale GitHub, pegainfer-project 729 ★Apache-2.0Updated 18 days ago

    git clone https://github.com/pegainfer-project/pegainfer.git
  16. rdc-cli

    Skills

    Scriptable CLI for RenderDoc captures — built for terminal workflows, CI pipelines, and AI agents

    Stale GitHub, BANANASJIM 186 ★MITUpdated 24 days ago

    git clone https://github.com/BANANASJIM/rdc-cli.git
  17. auto-deep-researcher-24x7

    Agents & frameworks

    🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.

    Stale GitHub, Xiangyue-Zhang 1,137 ★Apache-2.0Updated 5 months ago

    git clone https://github.com/Xiangyue-Zhang/auto-deep-researcher-24x7.git
  18. Search AI infrastructure, inspect facility evidence and explore sourced company relationships.

    Stale Official MCP Registry, com.gpuquant Updated 2 months ago 1 note

  19. Xcelsior GPU Cloud

    MCP servers

    Rent GPUs, launch spot instances and run serverless inference on the Xcelsior marketplace.

    Stale Official MCP Registry, io.github.aabiro Updated 11 days ago 3 notes

    @xcelsior-gpu/mcp@0.1.1
  20. Render farm GPU nodes: live availability, installed DCC apps and engines, per-minute cost.

    Stale Official MCP Registry, ru.evafarmstore Updated 39 days ago 1 note

  21. higgsfield

    AI repositories

    Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

    Stale GitHub, higgsfield-ai 6,021 ★Apache-2.0Updated 40 days ago

    git clone https://github.com/higgsfield-ai/higgsfield.git
  22. VMware Private AI (NVIDIA): GPU inventory, vGPU profiles, utilization, model serving — 20 tools

    Stale Official MCP Registry, io.github.vmware-skills Updated 5 days ago 1 note

    vmware-privateai@2.5.3
  23. Lium GPU Cloud

    MCP servers

    Rent NVIDIA GPU pods on Lium, run commands on them and remove them, billed per second.

    Stale Official MCP Registry, io.github.Datura-ai Updated 3 days ago 2 notes

    lium.io@0.45.1
  24. SpareHive GPU Advisor

    MCP servers

    Read-only GPU advisor: model VRAM needs, fit checks and rental prices, with evidence grades.

    Stale Official MCP Registry, io.github.RichardXu001 Updated 26 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.