Clash Mihomo for iOS/MacOS/Android/Windows/Linux

⚡️A native, local-first alternative to Logitech Options+, written in Rust 🦀 — remap buttons, DPI, and SmartShift over HID++. No account, no telemetry.

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

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。

CRS-自建Claude Code镜像，一站式开源中转服务，让 Claude、OpenAI、Gemini、Droid 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。

Turn HTML into a 500-page vector PDF in 1 second. Open source.

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

The universal proxy platform

Window peeking, alt-tab and other enhancements for macOS

Simple PDF generation for Python

React Hooks — 👍

A drop-in javascript spreadsheet library that provides rich features like Excel and Google Sheets

Feature-rich and customizable data grid React component

🐕 Bare minimum 500b fetch polyfill.

Excel Workbook Manager

A simple Python Pydantic model for Honkai: Star Rail parsed data from the Mihomo API.

A javascript-only SVG to PDF conversion utility that runs in the browser. Brought to you by yWorks - the diagramming experts

A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

A simple Python Pydantic model for Honkai: Star Rail parsed data from the Mihomo API.

OneBox is a cross-platform GUI client based on the sing-box kernel. \n Onebox 是一个基于sing-box 内核的跨平台图形客户端

🚀 现代化 sing-box 跨平台桌面客户端｜订阅导入・代理模式切换・运行态监控｜🪟 Windows / 🐧 Linux / 🍎 macOS。 Modern sing-box desktop client for subscriptions, proxy switching, and runtime monitoring.

Structured Outputs

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval (CVPR 2023)

High-accuracy NLP parser with models for 11 languages.

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction fine-tuning, reward model training, and support for PPO and DPO algorithms with various c…

A modular RL library to fine-tune language models to human preferences