Inference Bridge

Official reference implementation of the experimental Inference Provider API browser proposal.

Inference Bridge lets websites use AI chat through window.inference — with your permission, on a provider you choose in Options. Bring your own API keys for supported cloud providers, run a local model server, use on-device browser AI when available, or point the extension at an OpenAI-compatible endpoint you configure. Keys stay in the extension; page scripts never see them. • Streaming chat via window.inference.request() • Function tools and hosted web search on window.inference.request (page-executed function tools; keys stay in the extension) • Hosted web search when the selected provider supports it • Image input and output on window.inference.request when the selected model supports vision or image generation • Optional, default-off experimental bounded transcription and MP3 speech synthesis with separate per-site approval • Per-site Allow / Deny / Remember prompts • You pick the provider and model in Options • Optional host access is requested only for each custom server origin you save • Local loopback servers work without special CORS / ORIGINS setup • Injects only on https and localhost pages Official reference for the experimental Inference Provider API: https://github.com/SamSamskies/inference-provider-api Privacy policy: https://github.com/SamSamskies/inference-bridge/blob/main/PRIVACY.md