SQLite-style embeddable micro-VM runtime: run OCI/Docker images in hardware-isolated sandboxes—no daemon, no root.

Bash-based Git worktree manager with editor and AI tool integration. Automates per-branch worktree creation, configuration copying, dependency installation, and workspace setup for efficient parall…

A simple, performant and scalable JAX-based world modeling codebase.

crossing the streams

The developer framework for building analytics into your app on top of ClickHouse, Redpanda and other high-performance analytical infrastructure

JavaScript animation engine

UI over MCP. Create next-gen UI experiences with the protocol and SDK!

High performance Rust stream processing engine seamlessly integrates AI capabilities, providing powerful real-time data processing and intelligent analysis.

Roblox Foundation Model for 3D Intelligence

Typesafe APIs Made Simple 🪄

Securely run AI-generated code in stateful sandboxes that run forever.

OpenAPI support for tRPC 🧩

🦾 Take control of your AI agents

Inspect: A framework for large language model evaluations

Stainless full-stack API Framework

Agents Capable of Self-Editing Their Prompts / Python Code

a dead simple programming model for the cloud

Mamba SSM architecture

Chat language model that can use tools and interpret the results

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Resonate Server - A CLI, Durable Promise store, and Task Framework

Structured Outputs

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

Inference code for Llama models

A software engineering framework to jump start your machine learning projects

maximal update parametrization (µP)

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.