Lists (18)
Starred repositories
NVIDIA Alpamayo 2 Super is an open 34B multi-task foundation model designed to supercharge autonomous vehicle development.
Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning post-training, quantization, and deployment.
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Official PyTorch Implementation of "RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion" (CVPR 2025)
Visualize, query, and stream to train on multimodal robotics data.
High performance, multimodal-native engine for AI workloads.
[ECCV 2026] Official implementation of "ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device". A compact 6.1M-parameter network for zero-shot monocular depth estimation,…
NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced reasoning, navigation guidance, and visual question answering.
opensource NPU for LLM inference (this run gpt2)
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
A from-scratch C++17/ggml port of Depth Anything 3 (ByteDance)
A reusable Simulink framework for integrating Vision-Language-Action (VLA) models into robot manipulation workflows, featuring closed-loop control, Unreal Engine simulation, MATLAB-Python co-simula…
ArduPlane, ArduCopter, ArduRover, ArduSub source
MCP Toolbox for Databases is an open source MCP server for databases.
Ultra-Fusion: A Resilient Tightly-Coupled Multi-Sensor Fusion SLAM Framework under Sensor Degradation and Spatiotemporal Perturbation
A framework for unified end-to-end autonomous driving datasets processing
ROS plugin for OpenClaw, Claude (Code,Desktop,Dispatch), Codex, Google Gemini, Hermes, MCP, etc.
Control panel for VLLM, Sglang, llama.cpp, exllamav3
End-to-end UniAD C++ implementation - An autonomous driving system
[CVPR 2026] Beyond Generation: Advancing Image Editing Priors for Depth and Normal Estimation