A fully-hermetic Bazel GCC toolchain for Linux.

agent-native, drop-in Github Actions that can run locally or self-hosted in microvms, with debug-on-failure

Open source agent with local models built in. Fully private and offline. Works out of the box on any hardware.

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (for example, RadixAttention, Cache-aware scheduling)

The Best TypeScript framework for fine-tuning

A Chromium browser surface for OpenTUI using the Kitty graphics protocol

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

the runtime your coding agents live on

OpenCode Plugin for Local LLM Servers

llama-benchy - llama-bench style benchmarking tool for all backends

A Gaggia Classic control project using microcontrollers.

This project upgrades a Gaggia espresso machine with smart controls to improve your coffee-making experience. By adding a display and custom electronics, you can monitor and control the machine mor…

ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants

NEW ROCmfp4 format for llama.cpp

Israeli tech companies map

Vulkan header files and API registry

Self-hosted AI workspace.

Run LLMs with MLX

Swift API for MLX

LLMs and VLMs with MLX Swift

Home for the Development of MLX Vulkan backend