Stars
Real-time human motion capture and 3D body mesh generation for Apple Silicon (M4).
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
Dexbotic: Open-Source Vision-Language-Action Toolbox
Qwen3-TTS with nano vLLM-style optimizations for fast text-to-speech generation. Achieved 3x faster
Remote control for Antigravity — manage AI conversations, workspaces, and agents from any device. One command to set up, one URL to access.
A minimal Telegram agent powered by Claude Code, designed to be self-modifiable.
📱 Control your Antigravity AI sessions from your phone — real-time chat mirroring, multi-window management, and model switching via CDP
A token-efficient CLI for Lark/Feishu APIs, designed for AI assistants like Claude Code. Supports calendar, contacts, documents, and messages.
[CVPR 2026] EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents
Control Claude Code & Gemini CLI from your phone via Feishu. Broken config? Service down? Send one message — your AI agent diagnoses and fixes it while you're away
Voice mode for Gemini CLI
Official implementation of Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
[CoRL'22] PlanT: Explainable Planning Transformers via Object-Level Representations
[ICCV 2023 & ICLR 2026] VAD: Vectorized Scene Representation for Efficient Autonomous Driving
AI-powered, vision-driven UI automation for every platform.
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
Traversability mapping for mobile rough terrain navigation
Robot-centric elevation mapping for rough terrain navigation
Model Predictive Path Integral (MPPI) with approximate dynamics implemented in pytorch
ROS2 / FAST_LIO / PGO / Online Re-Localization / Consistent Map with BA or HBA
The navigation system for omnidirectional wheel robot in real world