Starred repositories
57
results
for sponsorable starred repositories
written in Python
Clear filter
A high-throughput and memory-efficient inference and serving engine for LLMs
The Python micro framework for building web applications.
scikit-learn: machine learning in Python
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
You like pytorch? You like micrograd? You love tinygrad! ❤️
Python sample codes and textbook for robotics algorithms.
Data validation using Python type hints
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
AI Agent Framework, the Pydantic way
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…
Pyodide is a Python distribution for the browser and Node.js based on WebAssembly
Incredibly fast crawler designed for OSINT.
🐍 Geometric Computer Vision Library for Spatial AI
Perform data science on data that remains in someone else's server
Light, flexible and extensible ASGI framework | Built to scale
Accessible large language models via k-bit quantization for PyTorch.
BoxMOT: Pluggable SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes
Simple, powerful, and fast logging for Python.
AI observability platform for production LLM and agent systems.
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure stra…
Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)
chDB is an in-process OLAP SQL Engine 🚀 powered by ClickHouse
A tool for refurbishing and modernizing Python codebases
🎡 Build Python wheels for all the platforms with minimal configuration.