Open-source speech AI models from KRAFTON, including Raon-Speech and Raon-SpeechChat for speech understanding, generation, and real-time full-duplex conversation.

Multimodal RL training framework for diffusion & omni models

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

Port of OpenAI's Whisper model in C/C++

Compile agent conversations!

The Vulkan API Specification and related tools

SwiftShader is a high-performance CPU-based implementation of the Vulkan graphics API. Its goal is to provide hardware independence for advanced 3D graphics.

A convenient CLI to streamline LiteRT related development workflows, including converting, quantizing, compiling, managing, running, benchmarking and visualizing LiteRT (TFLite) models on various h…

A modern model graph visualizer and debugger

AI Edge Quantizer: flexible post training quantization for LiteRT models.

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

Official repository of NeXt-TDNN for speaker verification

This repository contains the official implementation and pretrained weights for the paper "ReDimNet2: Scaling Speaker Verification via Time-Pooled Dimension Reshaping".

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

Support PyTorch model conversion with LiteRT.

LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization

AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world agent workflows.

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.

Native cross-format motorsport telemetry analysis workstation

Codex-assisted local 2D animation spritesheet generator and scene compositing workspace.

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

Latest dockerfiles and images for Deno - alpine, centos, debian, ubuntu

Rust bindings for the V8 JavaScript engine

self-hosted, distributed Durable Objects

Heterogeneous GPU Sharing on Kubernetes