Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
ipex-llm
AI repositoriesAccelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.
git clone https://github.com/intel/ipex-llm.git -
Kokon
MCP serversGenerate and edit images offline with Qwen-Image 2.1 on your GPU. Needs the Kokon desktop app.
kokon-mcp@0.12.1 -
runner
Agents & frameworksWhere terminal agents work together. Claude Code, Codex, Copilot CLI and pi on the same task, in one mission, each keeping its own TUI in a real terminal.
git clone https://github.com/yicheng47/runner.git -
GPU Cloud Prices (AWS, Azure, OCI)
MCP serversH100/H200/A100 on-demand AWS/Azure/OCI + Azure Spot; L4 AWS, L40S AWS/OCI. Cached $/hr, x402 $0.005
-
lilbee
MCP serversA local model engine with a search engine and web crawler built in. Run your coding agents on your own GPUs, and get cited answers from your files, code, and the sites you crawl. One executable.
git clone https://github.com/tobocop2/lilbee.git -
ShannonBase
AI repositoriesThe Next-Gen Database for AI—an infrastructure designed for data and AI. As the MySQL of the AI era.
git clone https://github.com/Shannon-Data/ShannonBase.git -
doomsday
SkillsDoomsday Network (DOOM) — Sovereign Layer-1 Proof-of-Work GPU Blockchain (SHA-256d CUDA), Zero-Fee PPLNS Pool, Remote MCP Server & 1:1 Base Mainnet DeFi Bridge (wDOOM)
git clone https://github.com/doomsday-network/doomsday.git -
wattindex
MCP serversGPU energy per million output tokens by model and GPU, with grid carbon intensity.
@reneturcios/wattindex@0.1.0 -
Ingero
MCP serverseBPF-based GPU causal observability with 7 MCP tools for AI-assisted GPU debugging
ghcr.io/ingero-io/ingero:v0.8.2 -
Lead Green
MCP serversGPU energy per million output tokens by model, GPU and configuration, with grid carbon by country.
leadgreen-mcp@0.3.1 -
runpod-plugins-official
MCP serversOfficial Runpod plugin for AI coding agents. Skills plus the hosted Runpod MCP server for managing pods, serverless endpoints, templates and volumes. Works with Claude Code, Codex and Gemini CLI.
git clone https://github.com/runpod/runpod-plugins-official.git -
ThinkTerm
Agents & frameworksA modern terminal with a built-in multiplexer: close it and your sessions keep running. Run shells and tons of AI agents across your machines, then pick them up from desktop, browser, TUI and more. Written in Rust with no UI framework: interface drawn straight on the GPU. No Electron, GPUI or webview.
git clone https://github.com/RoversX/ThinkTerm.git -
AI Compute Radar
MCP serversWhich open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
ai-compute-radar@1.2.1 -
AI Model Radar
MCP serversWhich open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
-
FitLLM
MCP serversWill this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
-
global-capacity-orchestrator-on-aws
MCP serversAI/ML and HPC at planetary scale. One API. Every Accelerator. Any Region. MIT-0 licensed.
git clone https://github.com/aws-solutions-library-samples/global-capacity-orchestrator-on-aws.git -
StudioTV LLM VRAM Calculator
MCP serversDoes an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.
-
ComputeNexa
MCP serversFind, launch and stop private GPUs on ComputeNexa, with a quote before anything is charged.
computenexa-mcp@0.1.0 -
OxiMux
Agents & frameworksA Rust-native, multi-agent development cockpit for macOS — spawn isolated worktrees, run CLI coding agents in parallel, and review every change through a GitLens-grade Git UX.
git clone https://github.com/nhtera/OxiMux.git -
kimi-k3-in-c
AI repositoriesA 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
git clone https://github.com/FareedKhan-dev/kimi-k3-in-c.git -
Nodegrove VRAM: can I run it?
MCP serversCan this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
@nodegrove/vram-mcp@1.1.5 -
paddler
AI repositoriesOpen-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.
git clone https://github.com/intentee/paddler.git -
skills
SkillsSkills for running, porting, profiling, and tuning code on Intel CPUs, GPUs, and the libraries and runtimes behind them.
git clone https://github.com/intel/skills.git -
navop
Agents & frameworksThree native apps on one kernel: Navop (databases, SSH/SFTP, terminal, remote desktop, AI), Navop Shell (SSH/SFTP, terminal, port forwarding, RDP/VNC) and Navop Data (SQL, Redis, MongoDB). Rust + GPUI.
git clone https://github.com/feigeCode/navop.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.