Building blocks for agents in C++

Hindsight: Agent Memory That Works Like Human Memory

Orchestrated autonomous Claude Code VMs on Fly.io

A desktop environment without graphics

Declaratively define and run required tools across environments, from local development to containerized cloud deployments.

Python SDK for mcpd

A free, open source, and extensible speech-to-text application that works completely offline.

An experimental operating system fully written in Rust, with a unikernel design, cooperative scheduling and a security model based on WASM sandboxing.

Blueprint by Mozilla.ai for generating podcasts from documents using local AI

A blazingly fast, open-source application server with type-safe APIs, built-in WebAssembly runtime, realtime, auth, and admin UI built on Rust, SQLite & Wasmtime.

JSON for Classic C++

A chat assistant to help you design experimental workflows in drug discovery using Ersilia models with ease!

The home of the Web Applets spec, demo and SDK

Structured Outputs

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

The fastai deep learning library

LLM training in simple, raw C/CUDA

A curriculum for learning about foundation models, from scratch to the frontier

A vector search SQLite extension that runs anywhere!

Create an IRC chat bot powered by AI, using llamafile, in minutes.

Text-To-Speech, RAG, and LLMs. All local!

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Perplexity Inspired Answer Engine

Your buddy in the (L)LM space.

Supercharge Your LLM Application Evaluations 🚀

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs