19 skills found
quinnjr / gpuGPU backend guidelines for skia-rs-gpu
aaguiarz / openfga-modeling-mcpMCP to assist on OpenFGA Modeling
hefarica / arbx-g-g005-advanced-react-19-usetransitionuseoptimisticMEV/arbitrage platform v2 - Rust hot-path + TS control-plane + CF Workers + Next.js
TongmingLAIC / ako4allDrive an agentic loop that iteratively optimizes a GPU kernel for maximum speedup. Use this skill whenever the user wants to optimize / speed up / benchmark a GPU kernel (CUDA, Triton, TileLang, C++, Python), mentions AKO / AKO4ALL / AKO4X / agentic kernel optimization, asks to "make this kernel fas…
Syngnat / GoNaviHigh-performance multi-data-source database client — ~30MB, AI & MCP ready, zero Electron bloat. | 高性能多数据源数据库客户端：约 30MB，AI 与 MCP 就绪，告别 Electron 膨胀。
Nikunj2003 / LLaMa-MCP-StreamlitAI assistant built with Streamlit, NVIDIA NIM (LLaMa 3.3:70B) / Ollama, and Model Control Protocol (MCP).
lemonade-sdk / lemonadeLemonade 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
gtwatts / mainframeAI-Native Bash Runtime with LSP & MCP | 2,000+ pure bash functions | Zero dependencies | Safe execution, structured output, first-time correctness for AI agents
mixpeek / amuxOpen-source control plane for AI coding agents — run, monitor & orchestrate dozens of parallel Claude Code, Codex & Gemini sessions from one web dashboard or your phone. Self-healing, single-file, tmux-native.
mixpeek / amuxOpen-source control plane for AI coding agents — run, monitor & orchestrate dozens of parallel Claude Code, Codex & Gemini sessions from one web dashboard or your phone. Self-healing, single-file, tmux-native.
raullenchai / Rapid-MLXThe fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
Trompetilla / nvidia-image-genGenerate and edit images using NVIDIA FLUX models
NVIDIA-AI-Blueprints / video-search-and-summarizationNVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting.
BlueStarSystem / aura-uiVibrant Depth UI component library for Laravel + Livewire + Alpine.js + Tailwind CSS
nmerget / t3dsTanStack Dokploy Directus DaisyUI Starter - A modern full-stack monorepo with TanStack Router, Query, Directus CMS, and DaisyUI components
snowdreamtech / ubuntuDocker Images for Ubuntu. (amd64, arm32v7, arm64,ppc64le,riscv64,s390x)
Intradyne / AnyLoom-AnythingLLM-Local-AI-agentic-DyTopo-swarmChatGPT-like AI that runs 100% locally on your hardware. No subscriptions, no cloud, complete privacy. Multi-agent swarm + 10 MCP tools + hybrid RAG vector DB + . Runs on one GPU (RTX 5090 recommended)
su-kaka / gcli2api将 GeminiCLI 和 Antigravity 转换为 OpenAI 、GEMINI 和 Claude API 接口
beeswaxpat / ffmpeg-render-proParallel video rendering with live dashboard, GPU auto-detection, and stream-copy concat. MCP server with 7 typed tools for AI agents, a Claude Code skill, and a CLI.
