Extremely fast Query Engine for DataFrames, written in Rust

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data

Moved to Codeberg

Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Official inference framework for 1-bit LLMs

One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure

1️⃣🐝🏎️ The One Billion Row Challenge -- A fun exploration of how quickly 1B rows from a text file can be aggregated with Java

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Production-ready platform for agentic workflow development.

Integrate cutting-edge LLM technology quickly and easily into your apps

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

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Source code for the X Recommendation Algorithm

🌙 LunarVim is an IDE layer for Neovim. Completely free and community driven.

A Python package to assess and improve fairness of machine learning models.

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

Rust bindings for the Python interpreter

A collection of libraries to optimise AI model performances

Inference code for Llama models

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

LlamaIndex is the leading framework for building LLM-powered agents over your data.

Find and fix bugs in natural language machine learning models using adaptive testing.

Carbon Language's main repository: documents, design, implementation, and related tools. (NOTE: Carbon Language is experimental; see README)

A topic-centric list of HQ open datasets.

A toolkit for developing and comparing reinforcement learning algorithms.