Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
SkillMIT★ 4Few starsNo key
MCP server that lets AI coding agents search and pull real frontend code, UI components and design mockups from 27 open sources (shadcn/ui, Magic UI, Aceternity, FreeFrontend, three.js, drei and more)
Node.jsMIT★ 4Few starsNo key
MCP for styles.refero.design — natural-language search across the curated DESIGN.md library.
Node.jsMIT★ 19No key
Production-ready Claude Code configuration. 12 original agents, 200+ slash-command skills, 45+ MCP servers, 14 plugins, design + 3D + WebGPU + GSAP + RAG tooling. One-command Node.js installer for pre
Node.jsMIT★ 7No key
3,287 open-source icons for AI-era software — agents, MCP, RAG, LLMs — with an MCP server so your coding assistant picks real names. React, Vue, Svelte, Solid, Preact, React Native, Astro, Laravel, Fl
Node.jsMIT★ 11No key
Search all your open tabs by title or full page content, and expose everything as RAG context for AI tools via MCP
Node.jsMIT★ 4Few starsNo key
Search 2,000+ real iOS interaction clips by describing the motion you want, then get compile-checked SwiftUI back. MCP server plus skill for Cursor, Grok and Claude Code.
Hosted by authorMIT★ 1Few starsNo key
Self-hosted multi-agent AI framework (LLM orchestrator) - web UI, voice, code & design studio, Home assistant, MCP plugins
SkillApache-2.0★ 4Few starsNo key
Discovers requirements and generates architectural, design, and deployment guidance for dynamic hybrid search systems by combining semantic search and keyword search. Optimized for AlloyDB hybrid sear
OfficialSkillApache-2.0★ 21k in collectionNo key
Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable enterprise search system in Google Cloud. Use when users need a
OfficialSkillApache-2.0★ 21k in collectionNo key
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
PythonApache-2.0★ 12kNo key
Redis Vector Library. The AI-native Python client for Redis.
OfficialPythonMIT★ 432No key
Your Cheat Sheet for AI Engineering Interview – Questions and Answers.
SkillApache-2.0★ 3.5kNo key
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
PythonApache-2.0★ 5.7kNo key
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
SkillMIT★ 11kNo key
Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scrat
SkillMIT★ 701No key
Java 8+ agentic SDK: unified LLM access (OpenAI/Anthropic/DashScope/Doubao/DeepSeek...),unified AI service(image/video/audio...), Tool Calling, MCP, RAG, SKILLS,Agent Runtime, A2A, agent blueprint, ag
SkillApache-2.0★ 435No key
Connect any MCP-compatible AI client (Claude Code, Cursor, Windsurf) to Unity or Godot. 275+ granular tools, an editor aware system prompt, game design document project context, script semantic search
PythonMIT★ 212No key
The pipe layer of an AI nervous system — one interface connecting provider neurons to your application, across three inference types: generate, stream, and a calibrated decide (via TypeSafe Jev). MCP-
Node.jsMIT★ 156No key
Pinecone's official Agent Skills library, for use with agentic IDEs such as Cursor, Github Copilot, Antigravity, Gemini CLI and more.
OfficialSkillMIT★ 15No key
Frontend AI coding agent platform with CLI, VS Code extension, desktop app, MCP server, RAG planning, Skills, SDD guardrails, browser automation, and LoRA planner models | 面向前端工程的 AI Agent 平台,支持 CLI、V
Node.jsMIT★ 120No key
Local-first photo library for Mac and Windows. Browse, cull and search thousands of photos and RAWs, find people and places on-device, and edit with LUTs, text, stickers, camera frames and collages. A
SkillMIT★ 243No key
Declarative AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run
PythonMIT★ 118No key
Who stands behind it