Tongyi Deep Research, the Leading Open-source Deep Research Agent

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

TradingAgents: Multi-Agents LLM Financial Trading Framework

ScreenCoder — Turn any UI screenshot into clean, editable HTML/CSS with full control. Fast, accurate, and easy to customize.

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

A Survey of Direct Preference Optimization (DPO)

An open-source AI agent that brings the power of Gemini directly into your terminal.

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

The #1 open-source SWE-bench Verified implementation

[NeurIPS 2025 D&B] 🚀 SWE-bench Goes Live!

Universal memory layer for AI Agents

[NeurIPS'25] GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

Prompt, run, edit, and deploy full-stack web applications using any LLM you want!

[NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis

The official code repository for the FullFront benchmark

Official inference repo for FLUX.1 models

Your AI Operator for Web, Android, Automation & Testing.

A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

[ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"

[arXiv 2023] Set-of-Mark Prompting for GPT-4V and LMMs

PyTorch code and models for the DINOv2 self-supervised learning method.

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

Official Repository of "Learning to Reason under Off-Policy Guidance"