Efficient Retrieval Augmentation and Generation Framework for building generative models and applications.
Open source machine learning framework to automate text- and voice-based conversations, enabling the creation of chatbots and voice assistants.
Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.
AutoAgent is a fully-automated, zero-code framework for creating and deploying LLM agents using natural language.
A visual playground for agentic workflows that allows AI engineers to iterate over agents 10x faster.
The TypeScript AI agent framework for building AI applications with support for various LLMs.
Customize your arXiv recommendation every day.
Everything you need to know to build your own RAG application.
FlashMLA is an efficient MLA decoding kernel optimized for Hopper GPUs, delivering significant performance improvements.
A Next.js project template for building conversational web applications.
HeadInfer is a memory-efficient inference framework for large language models that reduces GPU memory consumption.
Chrome / Edge extension to turn arXiv papers into Markdown codes in one click.
