MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
The MCP-RAG project is an AI agent framework based on the Multi-Context Protocol that connects various data sources (MySQL, documents, RAG search) with LLMs. It supports HTTP API, SSE chat, an MCP rou
GoApache-2.0★ 9No key
An AI agent gateway built on Temporal: governed, durable MCP tool calls with human sign-off, shared across teams with Temporal Nexus.
SkillMIT★ 1Few starsNo key
Chat-Anything is my custom evolution of RAG-Anything and rag-web-ui — a unified, intelligent chat system built to interact with any knowledge source. It combines Retrieval-Augmented Generation (RAG) w
SkillMIT★ 3Few starsNo key
Local RAG application to chat with PDF documents using Ollama and LangChain. Features both Streamlit web UI and terminal interface. No API keys required - runs entirely offline.
SkillMIT★ 1Few starsNo key
Curated collection of LLM apps built with RAG, AI Agents, Multi-agent Teams, MCP, Voice Agents and more
SkillApache-2.0★ 2Few starsNo key
Empathetic AI engineering partner with cognitive memory, multi-agent orchestration (10 agents), 132-signal skill routing, and self-improving reflection loops. Built on Model Context Protocol. By Aldo
Node.jsMIT★ 3Few starsNo key
Event-driven personal AI agent platform. Rust kernel + NATS JetStream + ArangoDB knowledge graph + plugin architecture. Always-on, extensible, language-agnostic.
SkillMIT★ 4Few starsNo key
A LLM chat UI with MCP support, Full RAG built with LangchainGo + Ollama + QDrant + Bubbletea.
GoApache-2.0Few starsNo key
End to end RAG pipeline over PDFs, articles and Slack: embeddings, pgvector search, grounded answers, plus an MCP server.
MCPLink onlyFew stars
Self-hostable, MCP-native memory backend for teams of humans and AI agents. A FastAPI service enforces a tagging contract (team/project scope, visibility, confidence, truth level, source, validation)
SkillMIT★ 2Few starsNo key
Multi-agent chat system with intent routing, tool calling (MCP), RAG, and real-time streaming. An orchestrator routes queries to specialized agents, evaluates response quality, and forwards to another
SkillMITFew starsNo key
https://www.ccwithai.com/blog/private-whatsapp-ai-agent-admin-dashboard
MCPLink only★ 2Few stars
A cache for your mind - AI chat grounded in what you actually know
SkillMITFew starsNo key
This is my attempt at creating a local RAG mcp server to chat with local docx, xlsx files.
MCPLink only★ 2Few stars
Local AI workstation dashboard Neuralforge— manage LLMs, agents, RAG, Telegram AI bot with 14 meme personas & voice cloning, image/video/3D generation, and LoRA fine-tuning and SMM module from a singl
SkillMIT★ 7No key
Open-source AI employees that ask before they act. 46 business roles, approval-gated autonomy, sandboxed code, Graph RAG on your own documents, WhatsApp/Telegram/Discord, Gemini, Anthropic, Ollama and
SkillMIT★ 19No key
AI 应用平台（聊天、绘画、知识库、工作流、 MCP服务市场、语音输入输出、长期记忆） | AI application platform (Chat,Draw,RAG,Workflow,MCP marketplace, ASR,TTS, Long-term memory etc)
SkillMIT★ 1.4kNo key
Zenn AI Agent Hackathon（第1〜3回）作品の検索システム。MCP Server + Agentic RAG Chat Web UI
SkillMITFew starsNo key
Local-first GenAI lab with a React frontend and Spring Boot backend, supporting Ollama, Amazon Bedrock, Hugging Face, RAG document retrieval, MCP-backed AWS tools, streaming chat, persistent sessions,
SkillMIT★ 7No key
Terminal-based chatbot application using local Ollama models with RAG, database access, and MCP integration
SkillMITFew starsNo key
An end-to-end RAG pipeline integrating MCP server with Vertex AI for intelligent chat summarization. Combines LLMs, document retrieval, and API orchestration to deliver contextual, real-time summaries
MCPLink onlyFew stars
Batuk is a sovereign AI chat workspace for local and hosted models, with multi-provider support, document chat, voice, web search, guardrails, auth, and local-first persistence.
SkillMIT★ 6No key
Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. Join our Discord https://discord.gg/VuxzM8m
PythonApache-2.0★ 86kNo key
Who stands behind it
