Command line helpers for fuzzing

Stream, transform, and route PostgreSQL data in real-time.

Train transformer language models with reinforcement learning.

Tile primitives for speedy kernels

More relighting!

The open-source, model-agnostic alternative to OpenAI's structured outputs for your own documents or the web.

Code & Dataset for Paper: "Distill Visual Chart Reasoning Ability from LLMs to MLLMs"

Get your documents ready for gen AI

Sleeping Mac = Bluetooth off

GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

A python package for serving LLM on OpenAI-compatible API endpoints with prompt caching using MLX.

Putting a brain behind `cat`🐈‍⬛ Integrating language models in the Unix commands ecosystem through text streams.

FastKafka is a powerful and easy-to-use Python library for building asynchronous web services that interact with Kafka topics. Built on top of Pydantic, AIOKafka and AsyncAPI, FastKafka simplifies …

State machine pattern for Rust

Blazing fast whisper turbo for ASR (speech-to-text) tasks

Software to implement GoT with a weviate vectorized database

Automate browser-based workflows with LLMs and Computer Vision

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

A flexible distributed key-value datastore that is optimized for caching and other realtime workloads.

LLM based autonomous agent that conducts local and web research on any topic and generates a comprehensive report with citations.

A simple screen parsing tool towards pure vision based GUI agent

Our main browser engine repository.

Flexible level editor

A TOML toolkit written in Rust

Home of OpenVMM and OpenHCL.

Arch is an intelligent prompt gateway. Engineered with (fast) LLMs for the secure handling, robust observability, and seamless integration of prompts with APIs - all outside business logic. Built b…

Building AI agents, atomically

Fast and accurate automatic speech recognition (ASR) for edge devices

Official inference framework for 1-bit LLMs