OSS
Microsoft Foundry Local Reaches General Availability — Ship Offline AI Apps With Zero Cloud Costs Across Windows, macOS, and Android
Microsoft announced Foundry Local GA on April 9, 2026 — a cross-platform local AI runtime that runs inference with no cloud dependency, no network latency, and no per-token costs. The runtime is small enough to bundle inside application installers, enabling fully self-contained AI-powered desktop, mobile, and edge apps on Windows, macOS (Apple Silicon), and Android. For builders shipping local-first AI products, this eliminates the 'deploy your own inference' problem with production-grade, zero-dependency packaging.
↳ Follow the thread