Lists (8)
Starred repositories
A Large-Scale Multi-Modal Dataset for Human Activity Understanding Grounded in Motion-Captured 3D Pose Labels
A python module to repair invalid JSON from LLMs
StreamingVLM: Real-Time Understanding for Infinite Video Streams
一饭封神：一个基于 AI 的智能菜谱生成平台，支持中华八大菜系 + 国际料理，提供营养分析、酒水推荐、菜谱效果图生成等全方位烹饪指导。
⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.
ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
[CoRL 2025] Repository relating to "TrackVLA: Embodied Visual Tracking in the Wild"
这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。
ROS wrapper for Meta's Segment-Anything model
An open-source, self-hosted personal AI note tool prioritizing privacy, built using TypeScript .
Official Task Suite Implementation of ICML'23 Paper "VIMA: General Robot Manipulation with Multimodal Prompts"
Real-time webcam demo with SmolVLM and llama.cpp server
打灰机守护程序-利用开源AI视觉模型（smolVLM2）与 MediaPipe 库，在你打灰机时保驾护航
One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression
Check Original Repo https://github.com/hessiser/veritas
Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
The best free and open-source automated time tracker. Cross-platform, extensible, privacy-focused.
A self-hosted, Markdown file based task management board
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
YOLO-UniOW: Efficient Universal Open-World Object Detection
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution
An AI companion for reading papers.