#onnx

Fast and accurate AI powered file content types detection

Turn any computer or edge device into a command center for your computer vision projects.

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Lightweight, probably the fastest PaddleOCR SDK in TypeScript. Multilingual Support. Runs anywhere JavaScript runs: Node.js, Bun, Deno, mobile react-native, web browsers, and browser extensions. Docker & CLI supported. The official SDK is browser-only.

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Simplify your onnx model

Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine.

A Toolkit to Help Optimize Onnx Model

Shared foundation for building MCP servers -- Streamable HTTP transport, OAuth 2.1, browser-based credential setup, and a shared embedding daemon.

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

MuJoco Simulation on Web Assembly with Neural netwroks

Visualizer for neural network, deep learning and machine learning models

ONNX neural network inference engine

State of the Art Natural Language Processing

A lightweight Python package for Automatic Speech Recognition using ONNX models

Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!