Stars
Lightweight coding agent that runs in your terminal
A workshop that teaches you how to build your own coding agent. Similar to Roo code, Cline, Amp, Cursor, Windsurf or OpenCode.
The Future of Data Engineering — A CLI SQL client for the modern data stack, enabling AI-native context engineering for data.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Supercharge Your LLM with the Fastest KV Cache Layer
《Agentic Design Patterns》中文翻译版
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.
ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
Monitoring recent cross-research on LLM & RL on arXiv for control. If there are good papers, PRs are welcome.
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step (ACL'24)
Guide to using pre-trained large language models of source code
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
A tool for testing and comparing the performance of different Large Language Model APIs. 一个用于测试和比较不同大语言模型API性能的工具。
Aligning pretrained language models with instruction data generated by themselves.
A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
Implementation of Nougat Neural Optical Understanding for Academic Documents
A machine learning software for extracting information from scholarly documents
🦜🔗 The platform for reliable agents.
分享一些好用的 Dify DSL 工作流程，自用、学习两相宜。 Sharing some Dify workflows.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
A modular graph-based Retrieval-Augmented Generation (RAG) system
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.