MCP servers and skills: search, filter by where they run, and compare.
1–24 of 36 tools for “amd”
Clear allLemonade 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
in the readmeproject is built by the community for every PC, with optimizations by AMD engineers to get the most from Ryzen AI, Radeon, and Strix Halo PCs
SkillApache-2.0★ 5.9kNo key
Free offline speech-to-text & subtitles (SRT/VTT) in 99 languages on any GPU — AMD, NVIDIA, Intel, Apple. Whisper via whisper.cpp + MCP server for Claude, Codex, Gemini CLI.
PythonMIT★ 5No key
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
in the readmeLLMs, vision, voice, image, and video behind one API - **Any hardware**: NVIDIA, AMD, Intel, Apple Silicon, Vulkan, or CPU-only - **Multi-user ready**: API key auth
GoMIT★ 50kNo key
Open-source simulator for autonomous driving research.
in the skill textRecommended system * Intel i7 gen 9th - 11th / Intel i9 gen 9th - 11th / AMD Ryzen 7 / AMD Ryzen 9 * +32 Gb RAM memory * NVIDIA RTX 3070/3080/3090 / NVIDIA
SkillMIT★ 14kNo key
A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)
in the readmePython Version 
in the readmeStarted | CLI Reference | Configuration | Changelog | Roadmap *Demo: Analyzing 2 years of NVDA, AMD & SPY stock data (15,000+ lines of raw JSON) using DeepSeek V3.2* ## What
SkillMIT★ 730No key
Local text to textured GLB on an AMD Strix Halo iGPU (gfx1151): FLUX.2 klein, a Vulkan-only TRELLIS.2 engine, and humanoid auto-rigging with SkinTokens on ROCm. No Blender, no CUDA.
SkillLink only★ 44
MCP server for measured local-LLM benchmarks from the AGmind claim registry — AMD Strix Halo (Ryzen AI Max+ 395) llama.cpp numbers today, NVIDIA DGX Spark on the bench. search_claims, get_claim, list_
Node.jsApache-2.0★ 4Few starsNo key
🎨 Turn Claude Code and OpenClaw into a powerful design assistant with local ComfyUI, API integration, and a large pro prompt library.
in the readmeabove, or Linux (Ubuntu 20.04 or newer recommended). - **Processor:** Intel i5 or AMD Ryzen 5 or better. - **Memory (RAM):** Minimum 8GB, 16GB recommended for better performance
Node.jsMIT★ 9No key
ACMI — the open protocol for agent memory. Three keys: Profile / Signals / Timeline. Redis/Upstash-native, MCP-ready, multi-agent fleet coordination.
Node.jsMIT★ 5Needs a key
AI-assisted FPGA development across AMD Vivado, Anlogic TangDynasty, and Intel Quartus.
MCPLink only★ 57
Official Mingxin MCP server: signed AI-inference-storage benchmarks (KV cache tiering, +29-40% throughput on AMD MI308X), article search, ROI estimation.
Node.jsMITFew starsNo key
Consistency verdicts for MCP tool calls. A transparent stdio proxy that sits between any MCP client (Claude Code, Cursor, Codex, custom agents) and any MCP server.It solves the lost update of multi-ag
in the readmeall gateways on a machine share the version state. Claude Code example, AMD Ross Vivado server: ``` claude mcp add vivado-mcp --scope project --transport stdio --env
PythonApache-2.0Few starsNo key
Public, source-opaque reference-rate SDKs and MCP server for FLOPS compute price indices — every value carries a verify URL.
in the readmefamily spans many accelerator models (NVIDIA data-center and workstation GPUs plus AMD Instinct), not just H100 — enumerate the live set via `/v2/catalog/public` ; it grows
PythonApache-2.0★ 1Few starsNo key
Sugra MCP: connector between LLM agents and world data. 1,600+ endpoints from 160+ primary sources across 36 data domains. Published in Anthropic's Connectors Directory for Claude. Also listed in Open
in the readmehistory, and citing the source and freshness on every number: Compare NVIDIA, AMD and Intel over the past 12 months, answered live through the Sugra MCP
PythonMIT★ 3Few starsNeeds a key
A growing collection of AI coding skills for creative and productivity workflows. Image fetching, logo generation, presentations, video/audio processing, local image generation, and more. Works with C
in the skill textGenerate images locally with Stable Diffusion. Auto-detects hardware (Apple Silicon, NVIDIA, AMD, CPU) and picks the best model. Cross-platform. | | **Icons8** | Fetch icons, illustrations, and
SkillMIT★ 10No key
in the readmebehavior: - **CPU energy** — joules the code actually consumes, from real hardware telemetry (AMD uProf / Linux RAPL / macOS powermetrics), chosen automatically for the host. - **LLM tokens** — the
PythonMITFew starsNo key
Public MCP server for MELANY stock ratings by Market Eyes Live (marketeyeslive.com): conviction tiers, 0-100 composites, 8 factor scores for 600+ US stocks and ETFs. No API key.
in the readmefit), flagged risks, theme context, as-of date | | `compare_stocks` | `{ "symbols": ["NVDA", "AMD"] }` (2 to 5) | Side-by-side tiers, composites, and valuation, quality and momentum
Hosted by authorMIT★ 1Few starsNo key
in the readmereceives regular updates! ___ release version Build Image Binary Release ## Support for `ARM` & `AMD` Architecture along with `MCP` Support Download: - Release - Docker Hub - GitHub Container Registry ## Support
Hosted by authorMIT★ 6No key
An MCP (Model Context Protocol) wrapper for running local LLMs using llama-cpp-python
in the readmepip install llama-cpp-python --force-reinstall --no-cache-dir ``` **ROCm** (AMD GPUs): ```sh CMAKE_ARGS="-DGGML_HIPBLAS=on" uv pip install llama-cpp-python --force
PythonMIT★ 4Few starsNo key
程序一慢，会议室里人人都是神医：这个说加机器，那个说换语言。performance-patterns-skill 教 AI 先做分诊——把性能问题路由到对应的排查 playbook，Windows、WSL、Linux、CUDA 各有路径。性能优化的第一课：先量准，再下刀。
in the skill text它能帮你解决什么 - **代码审查**：识别串行累加器、伪共享、缺少 `restrict`、`vzeroupper`、SIMD 宽度不足等常见问题。 - **性能报告分析**：解读 VTune、AMD uProf、ETW/WPA、Linux `perf`、火焰图和 Nsight 提供的线索。 - **游戏与普通程序**：排查掉帧、CPU/GPU 利用率异常、线程扩展不佳、计算热点和运行环境问题
SkillMIT★ 3Few starsNo key
Who stands behind it
