Train transformer language models with reinforcement learning.

Experience macOS just like before

Asynchronous HTTP client/server framework for asyncio and Python

PyGWalker: Turn your dataframe into an interactive UI for visual analysis

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Supercharge Your LLM Application Evaluations 🚀

Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.

Memory for AI Agents in 6 lines of code

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.

Build ChatGPT over your data, all with natural language

Supercharge Your LLM with the Fastest KV Cache Layer

the portable Python dataframe library

Adding guardrails to large language models.

High-resolution models for human tasks.

🐢 Open-Source Evaluation & Testing library for LLM Agents

Convert scans of handwritten notes to beautiful, compact PDFs

👾 Open source implementation of the ChatGPT Code Interpreter

An async Python micro framework for building web applications.

Fuzzy String Matching in Python

Solutions for various coding/algorithmic problems and many useful resources for learning algorithms and data structures

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Schema validation just got Pythonic

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

Python library for implementing GraphQL servers using schema-first approach.