Cross-platform, fast, feature-rich, GPU based terminal

A REPL interface to interact with various LLMs like ChatGPT etc.

Download market data from Yahoo! Finance's API

A simple screen parsing tool towards pure vision based GUI agent

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

A flexible and efficient implementation of Flash Attention 2.0 for JAX, supporting multiple backends (GPU/TPU/CPU) and platforms (Triton/Pallas/JAX).

A Jax-based library for designing and training transformer models from scratch.

Minimal but scalable implementation of large language models in JAX

All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.

NanoGPT (124M) in 3 minutes

[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Train very large language models in Jax.

The AI toolkit for the AI developer

An extremely fast Python linter and code formatter, written in Rust.

Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

JavaScript LaTeX to HTML5 translator

s1: Simple test-time scaling

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Shared data types for building collaborative software

A Wick theorem kernel written in C++ and interfaced with Python

DeepSeek LLM: Let there be answers

Transient commands

A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.

Attention Kernels for Symmetric Power Transformers

Port tmux key bindings to WezTerm

Quick LLM lookups in Emacs

An AI Hedge Fund Team