Lists (1)
Starred repositories
Data Science Skills for AI agents like Claude Code
A portable data substrate for humans and their tools to think together.
A PyTorch native platform for training generative AI models
A JAX backend for Apple Metal Performance Shaders (MPS), enabling GPU-accelerated JAX computations on Apple Silicon.
Our library for RL environments + evals
An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently.
A collection of crates to make implementing Kubernetes operators easier
Repo for AI Compiler team. The intended purpose of this repo is for implementation of a PJRT device.
A cross-platform, safe, pure-Rust graphics API.
Hummingbird compiles trained ML models into tensor computation for faster inference.
EXO Gym is an open-source Python toolkit that facilitates distributed AI research.
Spin up any open LLM on rented GPUs (vast.ai/RunPod), serve it with vLLM or llama.cpp, and drive it from Claude Code via Claude Code Router. Pay by the hour.
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…
Know if your agent skill actually works. A lightweight evaluation harness that tracks a success rate across Claude Code, Codex, Pi, and Hermes.
Trace-based tensor compiler for Rust. Toy/educational ML framework based on StableHLO and PJRT.
A functional language with algebraic effects, multishot continuations, and native codegen
Generator for MLIR files from known front-ends
torchax is a PyTorch frontend for JAX. It gives JAX the ability to author JAX programs using familiar PyTorch syntax. It also provides JAX-Pytorch interoperability, meaning, one can mix JAX & Pytor…
The command-line frontend to transactional consistency checkers for black-box databases
Black-box transactional safety checker based on cycle detection