Stars
dsh-go — DeepSeek Harness 装进口袋：手机本机运行，也能遥控你的电脑。
An agent-native CAD SDK for language models to create, inspect, and reconstruct complex, editable 3D models.
HM3D-M³: A Benchmark for Multi-Agent, Multi-Modal, Multi-Object Goal Navigation
Novel writer plugin for DeepSeek Harness.
Use openai-codex models and image generation via ChatGPT OAuth for DeepSeek Harness.
OpenBeni browser robot racing with MuJoCo WebAssembly, ONNX policies and training source
ACDC4Robot: Automated Conversion of Description Conventions for Robots from Design to Learning
[ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
Ubuntu for Rockchip RK35XX Devices
A cross-platform, high performance renderer for Gaussian Splatting using Vulkan Compute. Supports Windows, Linux, macOS, iOS, and visionOS
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)
Every front-end GUI client for ChatGPT, Claude, and other LLMs
A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for c…
Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
Visual-Inertial-Leg Odometry For Legged Robots
Curated list of awesome tools, demos, docs for ChatGPT and GPT-3
Official MegEngine implementation of CREStereo(CVPR 2022 Oral).
OpenGV is a collection of computer vision methods for solving geometric vision problems. It is hosted and maintained by the Mobile Perception Lab of ShanghaiTech.
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8…