Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
FastFlowLM
AI repositoriesRun LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.
git clone https://github.com/ROCm/FastFlowLM.git -
Hyperloom
Agents & frameworksAn agentic system that auto-optimizes LLM workloads on AMD GPUs.
git clone https://github.com/AMD-AGI/Hyperloom.git -
LMCache
AI repositoriesLMCache: Supercharge Your LLM with the Fastest KV Cache Layer
git clone https://github.com/LMCache/LMCache.git -
vllm
AI repositoriesA high-throughput and memory-efficient inference and serving engine for LLMs
git clone https://github.com/vllm-project/vllm.git -
gufo
AI repositoriesThe open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and Windows.
git clone https://github.com/gufo-org/gufo.git -
Amdoren
Public APIsFree currency API with over 150 currencies
-
turnkeyml
Datasets & benchmarksNo-code CLI designed for accelerating ONNX workflows
git clone https://github.com/onnx/turnkeyml.git -
Amdahl
MCP serversOutbound optimization: messages in the sender's voice, and answers from your calls and CRM deals.
-
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 -
strix-halo-guide
Datasets & benchmarksEvidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.
git clone https://github.com/hogeheer499-commits/strix-halo-guide.git -
uccl
AI repositoriesUCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
git clone https://github.com/uccl-project/uccl.git -
lemonade
MCP serversLemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
git clone https://github.com/lemonade-sdk/lemonade.git -
ODS
Agents & frameworksODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
git clone https://github.com/Osmantic/ODS.git -
dstack
SkillsA unified orchestration layer for heterogeneous AI compute. It standardizes how to manage compute and run training and inference on GPU clouds, Kubernetes, VMs, or bare-metal clusters.
git clone https://github.com/dstackai/dstack.git -
qwen38-strix-halo-harness
Datasets & benchmarksAI coding agent harness for any hardware, local or cloud (OpenAI-compatible engines). Tuned for AMD Strix Halo: Qwen3.8 125B on the iGPU, NPU side-jobs, crash recovery, logged benchmarks.
git clone https://github.com/aic0d3r/qwen38-strix-halo-harness.git -
Vivado MCP Native
MCP serversNative MCP server for controlling AMD/Xilinx Vivado on Windows and Linux via persistent Tcl.
vivado-mcp-native@0.2.1 -
babelscribe
MCP serversOffline speech-to-text and SRT subtitles in 99 languages on your own AMD/NVIDIA/Intel/Apple GPU.
babelscribe@0.4.0 -
Vivado Red MCP
MCP serversDrive AMD Vivado from AI assistants, with Red Pitaya STEMlab 125-14 build and deploy flows.
vivado-red-mcp@0.5.0 -
MarvinLabs vram_fit
MCP serversWill a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
-
project-maya
AI repositoriesProject Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
git clone https://github.com/mw00/project-maya.git -
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
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.