Stars
DeepSeek Harness: Everything is a Plugin.
一个基于 Android 调试 API + 百度地图实现的虚拟定位工具，并且同时实现了一个可以自由移动的摇杆
slime is an LLM post-training framework for RL Scaling.
Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。
🐧 一个更完整、更优雅的 Linux Clash / Mihomo 代理运行平台
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
论文阅读助手，自动搜索 arXiv 论文、提取图表并结合上下文解析图表内容，生成结构化阅读笔记和调研报告，帮助你从读懂每张图开始读懂论文。Paper reading assistant that searches arXiv papers, extracts figures, analyzes them with surrounding context, and generates stru…
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
OpenClaw-RL: Train any agent simply by talking
Processed / Cleaned Data for Paper Copilot
Pangolin is a lightweight portable rapid development library for managing OpenGL display / interaction and abstracting video input.
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
An open source implementation of CLIP.
[CVPR 24] MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation
Jupyter notebook tutorials for MMSegmentation
U8glib library for monochrome displays, version 2
SGM，立体匹配StereoMatching最经典应用最广泛算法，4000+引用，兼顾效率和效果。完整实现，代码规范，注释清晰，博客教学！
🔠Foreign language reading and translation assistant based on copy and translate.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".