Starred repositories
We write your reusable computer vision tools. π
Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.
Portable file server with accelerated resumable uploads, dedup, WebDAV, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file, no deps
Python packaging and dependency management made easy
The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous β¦
Call any LLM API with cost tracking, guardrails, logging and load balancing. 1.8k+ models, 80+ providers, 50+ endpoints (unified + native format). Available as a Python SDK or Proxy Server (AI Gateβ¦
DSPy: The framework for programmingβnot promptingβlanguage models
Convert PDF to markdown + JSON quickly with high accuracy
The official Python library for the OpenAI API
A modular graph-based Retrieval-Augmented Generation (RAG) system
Deezer source separation library including pretrained models.
Write scalable load tests in plain Python ππ¨
Data validation using Python type hints
Fully open reproduction of DeepSeek-R1
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
π€ smolagents: a barebones library for agents that think in code.
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
The open source developer platform to build AI agents and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integrated platform.
DeepSeek Coder: Let the Code Write Itself
π€ The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
π The fast, Pythonic way to build MCP servers and clients
SGLang is a fast serving framework for large language models and vision language models.
The official Python SDK for Model Context Protocol servers and clients