- San Francisco
- @ggelango
Stars
Blazing-fast, minimal, library-first reimplementation of Codex
A Python library for LLM-based evaluation using weighted rubrics.
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
A fully customizable and self-hosted sandboxing solution for AI agent code execution and computer use. It features out-of-the-box support for backtracking, a simple REST API and Python SDK, automat…
KENSAT, Edge-AI Compute in Orbit - A 2U CubeSat that runs a large language model on-orbit. A power-gated NVIDIA Jetson Orin Nano executes neural-network inference in space, and the results are down…
Core abstractions for building event-driven architectures in Rust.
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
An interface library for RL post training with environments.
NSA Triton Kernels written with GPT5 and Opus 4.1
Ever used asyncio and wished you hadn't? A tiny (~400 lines) event loop for Python.
CLI tool for encoding utf8 text using language models
Official repository for our work on micro-budget training of large-scale diffusion models.
An open-source volume bot written in Node.JS for Raydium. Create fast and cheap volume for your token using JITO.
Simple repository for training small reasoning models
A comprehensive Rust SDK for seamless interaction with the PumpFun Solana program.