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.
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Claude skill: polished demo videos of web app features from a short YAML storyboard (Playwright recording, smooth zooms, captions, music).
SkillMIT★ 1Few starsNo key
多模态 RAG 智能体：MCP 协议 + GraphRAG + Cross-Encoder 精排 + 多 Agent 编排 + RAGAS 评估
SkillMIT★ 4Few starsNo key
CookHero是一个基于 LLM + RAG + Agent + 多模态的智能饮食与烹饪管理平台，支持智能菜谱查询、个性化饮食计划、AI 饮食记录、营养分析、Web 搜索增强，以及可扩展的 ReAct Agent / Subagent 工具体系，帮助厨房新手轻松成为“烹饪英雄”。
SkillApache-2.0★ 633No key
Static, client-side viewer for Ragnarok Online .rrf replay files. Drag-and-drop a replay; see damage / skill / kill stats. Brazilian Portuguese UI.
SkillMIT★ 6No key
Python toolkit for AI apps: RAG evaluation with ragas, a computer-vision boilerplate, adapters for LangChain, OpenCV, RF-DETR and Milvus, and an MCP server for code assistants. Docs in Indonesian.
PythonMIT★ 2Few starsNo key
Enterprise RAG pipelines with native IRIS vector search. 6 production implementations with RAGAS evaluation, LangChain, AWS/Azure configs. No external VectorDB required.
SkillMIT★ 6No key
Multi-namespace federated RAG platform — LangGraph + ChromaDB + MCP, with a Streamlit UI and RAGAS evaluation.
SkillMITFew starsNo key
Agentic RAG system for FAA aircraft maintenance Q&A — LlamaIndex + Gemini agent with MCP tool-calling, Qdrant hybrid search, and RAGAS-evaluated grounding
SkillMIT★ 1Few starsNo key
Production-grade multi-agent RAG system with a self-correcting LangGraph supervisor (Researcher, Synthesizer, Critic), agentic tool calling, hybrid search, and an MCP server. Built with Gemini 2.5 Fla
SkillMIT★ 2Few starsNo key
Agentic RAG over SEC filings, prices and trained forecasting models: LangGraph, pgvector hybrid retrieval, Langfuse, RAGAS/DeepEval, FastAPI + Gradio
SkillMIT★ 1Few starsNo key
A local-first MCP server for PDF knowledge bases and hybrid retrieval | 一个面向 PDF 知识库与混合检索的本地优先 MCP 服务
SkillMIT★ 2Few starsNo key
PythonMIT★ 1Few starsNo key
Production-grade MCP server that exposes AI agent quality evaluation (RAGAS faithfulness, precision, recall, response relevancy + custom JSON trace eval).
PythonMITFew starsNo key
Production-grade agentic RAG system built from scratch. LangGraph multi-agent orchestration, MCP, enterprise middleware, and RAGAS evaluation, with real production bugs diagnosed and fixed along the w
SkillMIT★ 4Few starsNo key
This project replaces error-prone, 2-day manual structural reviews with a 4-minute Agentic AI workflow that parses IFC models for code compliance. It ensures structural safety through real-time 3D vis
SkillMIT★ 1Few starsNo key
PythonMIT★ 1Few starsNeeds a key
LangGraph-based CI/CD QA orchestration with 14 agents, MCP integrations, Slack/Jira workflows, and quality scoring.
SkillApache-2.0★ 2Few starsNo key
Production-shaped agentic AI customer support platform: LangGraph + Gemini agent, RAG over Chroma, MCP tool calling, JWT auth, RAGAS eval dashboard, Prometheus/Grafana observability.
MCPLink only★ 3Few stars
A framework-neutral RAG evaluation skill with golden sets, regression gates, and script-domain checks.
SkillMIT★ 10No key
设计并实现了一个具备自主迭代检索（retrieve-grade-rewrite-expand）的 TraceAgentic RAG 系统。通过 LangGraph 驱动 Agent 进行多步规划、相关性评估、重写查询与扩展检索，并实时输出 rag_step 进度与完整检索溯源（Trace），有效降低幻觉并提升可解释性。集成 MCP 工具实现文档与结构化数据（Git/MySQL）联合查询，支持文档批
SkillApache-2.0★ 4Few starsNo key
Who stands behind it
