fast-graphrag

RAG that intelligently adapts to your use case, data, and queries

hallo2

Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation Jiahao Cui1*  Hui Li1*  Yao Yao3  Hao Zhu3  Hanlin Shang1  Kaihui Cheng1  Hang Zhou2  Siyu Zhu1✉️  Jingdong Wang2  1Fudan Univer

Integuru

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

Sana

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

lingua

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

pydoll

这是一个用于自动化操作 Chromium 内核浏览器的 Python 库。它通过原生 DevTools 协议（CDP）直接控制浏览器，无需依赖 WebDriver，支持绕过验证码、模拟真人交互、网页截图等功能。

Agent-S

Agent S: Use Computer Like a Human   🌐 S3 blog  📄 S3 Paper  🎥 S3 Video   🌐 S2 blog  📄 S2 Paper COLM 2025  🎥 S2 Video   🌐 S1 blog  📄 S1 Paper ICLR 2025  🎥 S1 Video     

Scrapling

🕷️ An undetectable, powerful, flexible, high-performance Python library to make Web Scraping Easy and Effortless as it should be!

openpi

暂无简介

VideoCaptioner

🎬 卡卡字幕助手 | VideoCaptioner - 基于 LLM 的智能字幕助手 - 视频字幕生成、断句、校正、字幕翻译全流程处理！- A powered tool for easy and efficient video subtitling.

F5-TTS

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

verl

👋 Hi, everyone! verl is a RL training library initiated by ByteDance Seed team and maintained by the verl community. verl: Volcano Engine Reinforcement Learning for LLMs verl is a flexible, efficient and production-ready RL training library for large language models L