AI Model Library: LLMs, Agents & Dev Tools

LingBot-World 2.0 – Ant Group's Robbyant Opens Source Real-Time Interactive World Model

LingBot-World 2.0 is a real-time interactive world model open-sourced by Robbyant, a research team under Ant Group. Its core breakthrough lies in advancing video generation from a "one-way viewing" pa...

Kimi K2.8 Preview Review: In-Depth Analysis of Moonshot AI's Next-Generation Mainstream Model

VDN-MiniMax-H3 – OpenVDN's Open-Source Video Generation Acceleration Solution

VDN-MiniMax-H3 is an open-source video generation acceleration solution developed by the OpenVDN team, based on architectural modifications and deep optimization of the MiniMax-H3 model. This solution...

ffmpeg-skill: Open-Source Toolkit for Programming Agents to Achieve Professional Local Video Editing Capabilities

ffmpeg-skill is an open-source Agent Skill designed for programming agents (such as Claude Code, Cursor, Codex). Its core value lies in enabling AI to invoke local FFmpeg just like a professional vide...

Ling-3.0-flash-VL – Ant Group's Open-Source Native Multimodal Large Model

Ling-3.0-flash-VL is the first open-source native multimodal large model in Ant Group's InclusionAI Bailing series. It is an extension of the MoE architecture from Ling-3.0-flash, with a total paramet...

H3-World – A World Model with Action Controllability Developed by Tencent in Collaboration with Universities

H3-World is an action-controllable world model developed collaboratively by Tencent, National University of Singapore, and The Hong Kong Polytechnic University. It is based on the MiniMax-H3 video gen...

Orbis – Visko's Real-Time World Model That Makes AI Video Streaming Like Live Broadcasting

Orbis is Visko's first Live Model (real-time world model), fundamentally changing the way AI videos are generated—no longer requiring minutes or even tens of minutes of offline rendering, but instead ...

MiniMax H3 Max: Live-level Speed and Ecosystem Evolution in Real-time Video Generation

MiniMax H3 Max is a real-time video generation model introduced by MiniMax, based on the open-source H3 model, with post-training and inference optimization. This model supports two input methods: tex...

E-Commerce Bench – A Long-Term E-Commerce Business Evaluation Benchmark Jointly Open-Sourced by Qwen and Taotian

E-Commerce Bench is a long-term e-commerce business evaluation benchmark jointly open-sourced by Alibaba's Qwen and Taotian Group. This benchmark enables LLM Agents to operate an online store in a sim...

Atlas – The World's First Multimodal World Model from World Labs

Atlas is the world's first multimodal world model introduced by World Labs, founded by Fei-Fei Li. This model natively understands text, images, videos, and 3D spatial information. By anchoring visual...