Lists (2)
Stars
拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construct…
Knowledge Agents and Management in the Cloud
Empowering RAG with a memory-based data interface for all-purpose applications!
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
🌐 WebWalker [ACL2025] & WebDancer [Preprint]
A Model Context Protocol server for searching and analyzing arXiv papers
Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
Build resilient language agents as graphs.
FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser & Trae AI (And other Open Sourced) System Prompts, Tools & AI Models.
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Set of tools to assess and improve LLM security.
Full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning.
Python APIs for web automation, testing, and bypassing bot-detection.
AI's query engine - Platform for building AI that can answer questions over large scale federated data. - The only MCP Server you'll ever need
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability
The official Python SDK for Model Context Protocol servers and clients
Model Context Protocol Servers
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!