A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

ETL, Analytics, Versioning for Unstructured Data

Get your documents ready for gen AI

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper

BAML is a language that helps you get structured data from LLMs, with the best DX possible. Works with all languages. Check out the promptfiddle.com playground

WebApps in pure Python. No JavaScript, HTML and CSS needed

A fast and efficient type assistant for Python, including tensor shape inference

Pythonic Stream-like manipulation of iterables.

A Python tool to enforce dependencies, using modular architecture 🌎 Open source 🐍 Installable via pip 🔧 Able to be adopted incrementally - ⚡ Implemented with no runtime impact ♾️ Interoperable with…

An extremely fast Python package and project manager, written in Rust.

Open-source platform for extracting structured data from documents using AI.

Out-of-the-box (OOTB) GUI Agent for Windows and macOS

The R Installation Manager

Resources for Survival Analysis

LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

Visualize decision trees in Python

Agentic components of the Llama Stack APIs

PraisonAI is a production-ready Multi AI Agents framework, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code soluti…

Rust framework for LLM orchestration

The engine of the RenderCV App

Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Wo…

Understand Human Behavior to Align True Needs

Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

Code for the EMNLP 2024 paper "Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps"

A modular graph-based Retrieval-Augmented Generation (RAG) system

Sparse autoencoders

LLM101n: Let's build a Storyteller

Draw datasets from within Jupyter.