Make websites accessible for AI agents

🐫 CAMEL: Finding the Scaling Law of Agents. The first and the best multi-agent framework. https://www.camel-ai.org

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

No fortress, purely open ground. OpenManus is Coming.

Medical o1, Towards medical complex reasoning with LLMs

HuatuoGPT, Towards Taming Language Models To Be a Doctor. (An Open Medical GPT)

Medical NLP Competition, dataset, large models, paper

Medical Multimodal LLMs

Official repository of ’Visual-RFT: Visual Reinforcement Fine-Tuning’

[IEEE TIP] TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes

Official Repository of paper OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference

✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.

🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Build multimodal language agents for fast prototype and production

Solve Visual Understanding with Reinforced VLMs

[KDD2025] Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective

Build Multimodal AI Agents with memory, knowledge and tools. Simple, fast and model-agnostic.

minimal-cost for training 0.5B R1-Zero

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types

Ola: Pushing the Frontiers of Omni-Modal Language Model

Fully open reproduction of DeepSeek-R1

InspireMusic: A Unified Framework for Music, Song, Audio Generation.

Witness the aha moment of VLM with less than $3.

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

😎丰富生态、🧩支持扩展、🦄多模态 - 大模型原生即时通信机器人平台 | 适配 QQ / 微信（企业微信、个人微信）/ 飞书 / 钉钉 / Discord / Telegram 等消息平台 | 支持 ChatGPT、DeepSeek、Dify、Claude、Gemini、xAI Grok、Ollama、LM Studio、阿里云百炼、火山方舟、SiliconFlow、Qwen、Moonshot…

Frontier Multimodal Foundation Models for Image and Video Understanding