Octomil
Octomil is the production control plane for on-device AI. Use it to serve models locally, ship them to devices, and monitor rollout health, quality, and fleet behavior from one system.
Quickstart
Get up and running with your first model or deploy to a phone.
Download
Download Octomil on macOS, Windows, or Linux.
Cloud
Dashboard for fleet health, rollouts, routing, and model versions.
API Reference
View Octomil's API reference.
SDKs
Python SDK
Model registry, responses, rollouts, and control-plane operations.
iOS SDK
On-device inference, deployment, and updates with CoreML.
Android SDK
On-device inference, deployment, and updates with LiteRT and TFLite.
Browser SDK
Run models in the browser with WebGPU and WASM.