Stars
Minimal implementation for communication between Zenoh and ROS2 DDS, supporting Python / Rust / C++.
Simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" represents "simulation and real"
DeepEvolve is a research and coding agent for new algorithm discovery in different science domains with Deep Research and AlphaEvolve.
An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.
The ultimate LLM/AI application development framework in Golang.
The absolute trainer to light up AI agents.
Implementation of UltraMem, improved Product Key Memory design, from Bytedance AI labs
Open-source Trading OS with pluggable AI brain | From market data → AI reasoning → Trade execution | Self-hosted & Multi-exchange
Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.
Real-time Semantic Visual SLAM augmented with gan-based image inpainting module
YOLOPv2: Better, Faster, Stronger for Panoptic driving Perception
Simple and Easy simulator YOLO Object Detection with Bird's Eye View
3D object detection using YOLO and depth estimation
Official implementation of the WACV 2025 ( Oral ) paper. RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision.
Open Source 3D Printed Robotic Arm for educational purposes
Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization
One-click training of your own GPT. Training a GPT has never been easier for beginners. / 一键从头训练一个LLM，0基础训练GPT原来可以这么简单？
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
A benchmark for LLMs on complicated tasks in the terminal
[NeurIPS 2025 spotlight] Official implementation for "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving"
A community driven registry service for Model Context Protocol (MCP) servers.
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.