Stars
将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。
Elevate your AI research writing, no more tedious polishing ✨
SkillsBench evaluates how well skills work and how effective agents are at using them.
🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
[arXiv 2023] Set-of-Mark Prompting for GPT-4V and LMMs
[NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents
Mailman 是一个功能强大的现代化邮件管理系统，提供邮件同步、智能解析、触发器自动化和AI助手等功能。支持多种邮件协议，具有直观的Web界面和强大的后端API。
一个基于FastAPI和现代Web技术构建的Outlook邮件管理系统，支持多账户管理、邮件查看、搜索过滤等功能。
AI Powered Email Aggregation Client | AI识别的邮件聚合客户端
Mobile-Agent: The Powerful GUI Agent Family
Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
AI比赛经验帖子 & 训练和测试技巧帖子 集锦（收集整理各种人工智能比赛经验帖）
Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"
✨✨Latest Advances on Multimodal Large Language Models
Automate your browser with GPT-4
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs