WinGet is the Windows Package Manager. This project includes a CLI (Command Line Interface), PowerShell modules, and a COM (Component Object Model) API (Application Programming Interface).

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

Image augmentation library in Python for machine learning.

Mimesis is a robust data generator for Python that can produce a wide range of fake data in multiple languages.

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

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.

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Faker is a Python package that generates fake data for you.

Improved file parsing for LLM’s

Accessible large language models via k-bit quantization for PyTorch.

Large Language Model Text Generation Inference

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

Integrate the DeepSeek API into popular softwares

Huly — All-in-One Project Management Platform (alternative to Linear, Jira, Slack, Notion, Motion)

DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis

All-in-One Development Tool based on PaddlePaddle

a small build system with a focus on speed

The Startup CTO's Handbook, a book covering leadership, management and technical topics for leaders of software engineering teams

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

FlashInfer: Kernel Library for LLM Serving

Toolkit for linearizing PDFs for LLM datasets/training

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

The collection of pre-trained, state-of-the-art AI models for ailia SDK

A lightweight data processing framework built on DuckDB and 3FS.

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support