CUA-Gym-Hub: mock web apps as reproducible RL training environments for computer-use agents

Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

Kimi Code CLI is your next CLI agent.

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

🙌 OpenHands: AI-Driven Development

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade features of agents.

Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (ACL 2026)

Inference, Fine Tuning and many more recipes with Gemma family of models

A High-efficiency Open-source Toolkit for Table-to-Latex Task

Tool for generating high quality Synthetic datasets

BioInformatics Agent (BIA): Unleashing the Power of Large Language Models to Reshape Bioinformatics Workflow

The Company AI Command Center

Lightweight coding agent that runs in your terminal

ProBench: Automatic Evaluation on Open-ended Multi-domain Expert Tasks

[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

[ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer

[CVPR 2025] Official Dataloader and Evaluation Scripts for VideoAutoBench.

Minimalistic large language model 3D-parallelism training

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

Codebase for Aria - an Open Multimodal Native MoE

Convert PDF to markdown + JSON quickly with high accuracy

The Library for LLM-based multi-agent applications

[Neurips 24' D&B] Official Dataloader and Evaluation Scripts for LongVideoBench.

LLM101n: Let's build a Storyteller

③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.