Local AI in any app — on every platform you ship to
DVAI Bridge embeds an OpenAI-compatible AI server inside your app. Your users get private, offline AI. You write the same code on every platform. Free for personal use. Every release turns into Apache 2.0 after three years.
Nine backends, one API
llama.cpp, MediaPipe, MLX, Transformers.js, WebLLM, LiteRT, ONNX Runtime, ML.NET, llamafile — all behind the same OpenAI HTTP wire. The engine picks itself per device.
Six SDKs, five registries
TypeScript, Swift, Kotlin, Dart, C#, with React Native and Capacitor wrappers on top. npm, Maven Central, CocoaPods, pub.dev, NuGet — pick the one for your stack.
Zero install for your users
Bridge is a library, not a product. It runs inside your app's own process — no sidecar, no Ollama, no Docker, no separate server for your users to install.
Pair across devices
A phone can offload heavy inference to a paired laptop on the same Wi-Fi — end-to-end encrypted. Or run a self-hosted rendezvous server for cross-network paths.
Licensing
Free for personal, educational, academic, evaluation, and internal-only use. Commercial use is a fair tiered royalty — the first £90,000 is free, then 4% / 6% / 8% on revenue bands. We publish pricing openly.
See the licensing model →Contributing
Pull requests, bug reports, and feature ideas welcome. Contributors sign a short Apache-style CLA so we can keep the dual-licensing model intact — you keep copyright in your contribution.
Read the CLA →