GitMCP is an open-source remote Model Context Protocol (MCP) server that transforms GitHub repositories (including codebases and GitHub pages) into real-time documentation centers, allowing AI tools (such as Cursor) to directly access and publish documentation...
NeuralAgent is an open-source desktop AI personal assistant that automates various complex tasks through natural language commands, such as simulating keyboard input, mouse clicks, browser navigation, form filling, and email sending. NeuralAgent...
self-llm (Open Source Large Model Usage Guide) is an open source large model tutorial created by Datawhale specifically for beginners in China. Based on the Linux platform, it provides a complete guide from environment configuration to model deployment and fine-tuning, covering LLaMA...
Glass is an open-source, stealth AI desktop assistant developed by the Pickle team. Glass can capture screen content and audio in real time in the background and transform it into structured knowledge. Glass's core functions include real-time meeting recording, automatic summarization, etc.
WrenAI is an open-source business intelligence AI agent tool from Canner. Through natural language interaction, it helps users quickly query, analyze, and visualize structured data without writing complex SQL code. Users simply need to use...
KittenTTS is a lightweight, open-source text-to-speech (TTS) model developed by the KittenML team. It features an extremely small model size (only 25MB) and powerful CPU optimizations, allowing it to run on low-power devices without a GPU...
DreamVVT is a video virtual try-on (VVT) technology jointly developed by ByteDance and Tsinghua University (Shenzhen). Based on the Diffusion Transformer (DiTs) framework, it achieves virtual try-on through a two-stage approach...
SkyReels-A3 is an advanced AI model launched by Kunlun Tech. Based on the DiT (Diffusion Transformer) video diffusion architecture, it combines frame interpolation, reinforcement learning, and camera movement control technologies. The model can use audio-driven techniques to transform photos or...
AionUi is a free, open-source, cross-platform desktop application built on Electron and React, which transforms the Gemini CLI command-line AI chat experience into a modern, efficient graphical interface. AionUi provides additional features...
Baichuan-M2 is an open-source medical augmentation model developed by Baichuan Intelligence. It has demonstrated outstanding performance in the medical field, achieving a score of 60.1 in the HealthBench benchmark, surpassing numerous open-source models such as OpenAI's gpt-oss120b, and reaching the top spot globally...
MiroThinker is an open-source family of intelligent agent models designed for deep research and solving complex, long-term problems. Built on Qwen3, the model features task decomposition, multi-hop inference, retrieval-enhanced generation, code execution, and more...
MiroFlow is a powerful framework for developing multi-agent systems, designed specifically for building complex, high-performance AI agents. It generates high-quality agent trajectory data for models such as MiroThinker. The framework boasts reproducible performance...
GLM-4.5V is the latest generation visual inference model from Zhipu Open Source. Built with 106B parameters and possessing 12B activation capability, it is currently a leading visual language model (VLM). The model is based on GLM-4.1V-Thinking...
Matrix-Game 2.0 is a self-developed world model released by Kunlun Tech's SkyWork AI. It is the industry's first open-source, general-purpose, real-time long-sequence interactive generation model, fully open-source, driving the development of the interactive world model field...
RynnVLA-001 is a vision-language-action model developed by Alibaba DAMO Academy. The model learns human operational skills through pre-training on a large number of first-person perspective videos and implicitly transfers them to the control of the robot arm.
RynnRCP is an open-source Robotics Context Protocol from Alibaba DAMO Academy, which enables seamless development of embodied intelligence. RynnRCP comprises two main modules: the RCP framework and RobotMotion...
RynnEC is a world understanding model (MLLM) developed by Alibaba DAMO Academy, specifically designed for embodied cognition tasks. The model comprehensively analyzes objects in a scene from 11 dimensions, including location, function, and quantity, supporting object understanding, spatial...
Matrix-3D is a framework developed by Kunlun Tech's Skywork AI team for generating explorable panoramic 3D worlds. The framework combines panoramic video generation with 3D reconstruction, starting from single images or text cues to generate high-quality, omnidirectional...
AI Sheets is an open-source, no-code data processing tool from Hugging Face. It provides an Excel-like interface, allowing users to easily invoke thousands of open-source AI models through natural language prompts to build, enrich, and...
Skywork UniPic 2.0 is a high-efficiency multimodal model open-sourced by Kunlun Wanwei, focusing on unified image generation, editing, and understanding capabilities. The model is based on the SD3.5-Medium architecture with 2B parameters, and utilizes pre-training and progressive dual-task training...
Voost is an innovative virtual try-on and try-off model from NXN Labs, developed based on the unified and scalable Diffusion Transformer (DiT) framework. It can handle both virtual try-on and try-off tasks simultaneously...
hunyuan-large-vision is a multimodal understanding model launched by Tencent. Based on the MoE architecture, it has 52-bit activation parameters and supports image, video, and 3D spatial input. The model has been showcased in the internationally renowned large-scale model arena, LMA Arena Vision...
Skywork Deep Research Agent v2 is an upgraded version of the deep research agent launched by Kunlun Tech. As the core engine of the Skywork super agent, it possesses multimodal deep research capabilities and integrates multimodal retrieval and understanding for the first time...
Mureka V7.5 is an advanced AI music creation model launched by Kunlun Wanwei Group. The model excels in Chinese song creation, accurately reproducing timbre and performance techniques, and enhancing pronunciation and emotional expression.