Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
It is the only official source for URDF models of the AgiBot X2 series, offering clear hardware version identification and both URDF and MuJoCo formats, making it essential for simulation and development with a real product line.
URDF models for the AgiBot X2 series humanoid robots.
| Model | Directory | Description |
|---|---|---|
| X2 Ultra | X2_URDF-v1.3.0/ | Flagship model |
| X2 Ultra (new version) | X2_URDF-v1.4.0/X2-Ultra.* | Upgraded motors, reinforced structure |
| X2 EDU | — | X2 人人造 (coming soon) |
Check the nameplate on the back of your robot's neck:
X2_URDF-v1.3.0/x2_ultra.*X2_URDF-v1.4.0/X2-Ultra.*├── X2_URDF-v1.3.0/ # X2 Ultra (flagship)
│ ├── x2_ultra.urdf # Full model
│ ├── x2_ultra_simple_collision.urdf # Simplified collision
│ ├── x2_ultra.xml # MuJoCo format
│ ├── x2_fist.urdf # Dummy fist end-effector
│ ├── x2_fist.xml # Dummy fist end-effector (MuJoCo)
│ ├── scene.xml # Scene file
│ ├── meshes/ # Mesh files (STL)
│ ├── visual/ # Preview images
│ └── README.md
│
└── X2_URDF-v1.4.0/ # X2 Ultra (new version)
├── X2-Ultra.urdf # X2 Ultra (new version) — full model
├── X2-Ultra_simple_collision.urdf # X2 Ultra (new version) — simplified collision
├── X2-Ultra.xml # X2 Ultra (new version) — MuJoCo format
├── scene.xml # Scene file
├── meshes/ # Mesh files (STL)
├── visual/ # Preview images
└── README.md
pip3 install mujoco
python3 -m mujoco.viewer --mjcf X2_URDF-v1.3.0/scene.xml
Or launch the viewer and drag-and-drop the XML file into the window.
Install the URDF Visualizer extension.
AgiBot is a robotics company building general-purpose humanoid robots. Learn more at official website.
This project is licensed under the Mulan PSL v2 (木兰宽松许可证, 第2版). See LICENSE for details.
URDF models for AgiBot X2 series -- 智元灵犀X2系列 URDF
Similar projects matched by category, topics, and programming language.
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.

A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.