ZeroFS - The Filesystem That Makes S3 your Primary Storage

Par (⅋) is an experimental concurrent programming language. It's an attempt to bring the expressive power of linear logic into practice.

AI coding agent, built for the terminal.

The example code for my uv in Product Part 2 video

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.

Scaling RL on advanced reasoning models

Rules and Knowledge to work better with agents such as Claude Code or Cursor

A framework for optimizing DSPy programs with RL

Quantitative risk and performance analysis package for financial time series powered by the Julia language.

Helping you select an AI agent framework

This is the official repository for The Hundred-Page Language Models Book by Andriy Burkov

Easiest way to give context to LLMs; Attachments has the ambition to be the general funnel for any files to be transformed into images+text for large language models context by only adding 2 lines …

LLM-driven assistant for analyzing, understanding and optimizing systems

TWIX is an open-source data extraction tool that reconstructs structured data from documents at scale, accurately and at low cost, by inferring the shared underlying visual template across documents

A system for agentic LLM-powered data processing and ETL

LLM agents built for control. Designed for real-world use. Deployed in minutes.

Effortlessly run LLM backends, APIs, frontends, and services with one command.

LOTUS: A semantic query engine for fast and easy LLM-powered data processing

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.

Fast State-of-the-Art Static Embeddings

GritQL is a query language for searching, linting, and modifying code.

Quantitative analysis, strategies and backtests

Features and labels engineering of raw data of quotes of several stocks.

A multi-factor equity risk model for quantitative trading.

Neural Search

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)