仅需Python基础，从0构建自己的具身智能机器人；从0逐步构建VLA/OpenVLA/SmolVLA/Pi0， 深入理解具身智能

Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.

特厨探店/隋坡老师 的探店视频AI总结

OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

DeepSeek Harness: Everything is a Plugin.

A markup-based typesetting system that is powerful and easy to learn.

A native iOS/iPadOS editor for Typst — the modern typesetting system.

The slightly more awesome standard unix password manager for teams

A simple, yet elegant, HTTP library.

The best way to control Claude Code, Codex and more from any computer or phone

Browser-native visualization for embodied AI data (MCAP, ROS bag, HDF5)

Open ROS 1 and ROS 2 bags (.mcap, .db3, .bag), PX4 logs, point clouds and Gaussian splats in your browser. No install, no upload. Open source Foxglove alternative.

Open-source unified multimodal model

[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

A pure Unix shell script ACME client for SSL / TLS certificate automation

UniLab: Contract-driven infrastructure for robot learning across physics backends and hardware

阿里云盘命令行客户端，支持JavaScript插件，支持同步备份功能。

The agent that grows with you

[ECCV 2026] TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation

An elegant PyTorch deep reinforcement learning library.

AI agents running research on single-GPU nanochat training automatically

Framework for measuring sim-to-real gaps in robot joint motions. Supports different humanoids with physics simulation, real hardware data collection, and statistical analysis.

PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursively self-improve through agentic workflows.

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

[CVPR 2026 Oral] Learning to Drive via Real-World Simulation at Scale