This library performs non-blocking inference on TensorRT models.

Engine-agnostic semantic profiler for LLM inference systems (vLLM, SGLang, TensorRT-LLM, NVIDIA Dynamo)

ONNXRuntime Node.js binding

Local multi-format deployment-artifact analysis for on-device AI models

Build and deploy custom ML containers on AWS SageMaker with minimal configuration.

ONNX Runtime Plugin for Unity

RAW CLI — #1 GPU & bare metal servers for AI companies. Deploy vLLM, Ollama, Llama, CUDA inference. CPU from $9/mo, GPU from $304/mo. 90% cheaper than AWS.

ONNXRuntime Node.js binding

Owner-run mswarm node for exposing local mcoda agents through the mswarm self-hosted gateway.

ONNX Runtime for Unity - Windows x64 GPU Provider

ONNX Runtime for Unity - Linux x64 GPU Provider

ONNXRuntime Node.js binding

ONNX Runtime Extensions for Unity

ONNX Runtime Utilities for Unity

ONNX Runtime Generative AI for Unity

Cortex is an openAI-compatible local AI server that developers can use to build LLM apps. It is packaged with a Docker-inspired command-line interface and a Typescript client library. It can be used as a standalone server, or imported as a library.

Embed compressed documentation indexes into AGENTS.md/CLAUDE.md for AI coding agents

fast GPU inference with onnxruntime using cuda_interop on Unity

Runtime-configurable Pi package for safe GPU inference SRE, token efficiency analysis, and proposal-only optimization workflows.

<p align="center"> <img alt="cortex-cpplogo" src="https://raw.githubusercontent.com/janhq/cortex/dev/assets/cortex-banner.png"> </p>