🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Python tool for converting files and office documents to Markdown.

Animation engine for explanatory math videos

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

💫 Toolkit to help you get started with Spec-Driven Development

Universal memory layer for AI Agents

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

A generative speech model for daily dialogue.

⚡ A Fast, Extensible Progress Bar for Python and CLI

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

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone

The official Python SDK for Model Context Protocol servers and clients

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

OCR, layout analysis, reading order, table recognition in 90+ languages

Agentic IM Chatbot infrastructure that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

Source Han Sans | 思源黑体 | 思源黑體 | 思源黑體 香港 | 源ノ角ゴシック | 본고딕

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

match command-line arguments to their help text

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Spark-TTS Inference Code

Refine high-quality datasets and visual AI models

Code for the manim-generated scenes used in 3blue1brown videos

Supervisor process control system for Unix (supervisord)

The most powerful Android RPA agent framework, next generation of mobile automation robots.

Large World Model -- Modeling Text and Video with Millions Context

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms

📄 Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVINO, MNN, PaddlePaddle and PyTorch.

Automatic integrate all Xiaomi devices to HomeAssistant via miot-spec, support Wi-Fi, BLE, ZigBee devices. 小米米家智能家居设备接入Hass集成

The simplest, fastest repository for training/finetuning small-sized VLMs.