Collection of papers from the Goldman Sachs Quantitative Strategies Research Notes series (published in the '90s)

C++20 idiomatic APIs for the Apache Arrow Columnar Format

An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.

Helpful, quality prompts for full SDLC.

The State Of The Art, intelligence

Wrapper around tool using LLMs for agentic workflows

ZeroFS - ZeroFS serves S3-compatible buckets as POSIX filesystems over NFS and 9P, or as raw block devices over NBD.

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

The open source coding agent.

The example code for my uv in Production 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.

Standards for building agents, better

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

Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.

Optimized LLM-Powered Data Processing: up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code

🚀🤖 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