Python packaging and dependency management made easy

Certbot is EFF's tool to obtain certs from Let's Encrypt and (optionally) auto-enable HTTPS on your server. It can also act as a client for any other CA that uses the ACME protocol.

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Convert PDF to markdown + JSON quickly with high accuracy

Distributed Task Queue (development branch)

Fully open reproduction of DeepSeek-R1

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

GUI for a Vocal Remover that uses Deep Neural Networks.

Tornado is a Python web framework and asynchronous networking library, originally developed at FriendFeed.

Rembg is a tool to remove images background

Maple Mono: Open source monospace font with round corner, ligatures and Nerd-Font icons for IDE and terminal, fine-grained customization options. 带连字和控制台图标的圆角等宽字体，中英文宽度完美2:1，细粒度的自定义选项

Fast and memory-efficient exact attention

SGLang is a fast serving framework for large language models and vision language models.

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

Faster Whisper transcription with CTranslate2

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Stable Diffusion with Core ML on Apple Silicon

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Retrieval and Retrieval-augmented LLMs

thumbor is an open-source photo thumbnail service by globo.com

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Hackable and optimized Transformers building blocks, supporting a composable construction.

Refine high-quality datasets and visual AI models

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型