Starred repositories
Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
Universal skills loader for AI coding agents - npm i -g openskills
100+ Fine-tuning Tutorial Notebooks on Google Colab, Kaggle and more.
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agen…
Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.
Kronos: A Foundation Model for the Language of Financial Markets
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed …
Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
A simple, easy-to-hack GraphRAG implementation
The open-source CapCut alternative
Jupyter Notebooks to help you get hands-on with Pinecone vector databases
Repo for the Complete Agentic AI Engineering Course
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…
A flexible, adaptive classification system for dynamic text classification
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
ContextGem: Effortless LLM extraction from documents
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
General technology for enabling AI capabilities w/ LLMs and MLLMs
[COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
This is a collection of our NAS and Vision Transformer work.
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。
An open protocol enabling communication and interoperability between opaque agentic applications.