Model-connected feature

Full-stackReleased · Preview

Add AI Chat to your React app.

BTST adds streaming APIs, model integration, conversation history, routes, and customizable chat UI while your app controls access and provider costs.

Best for

React teams that already know which AI SDK model provider they want and need chat history, tools, and product UI inside their app.

Requires
An AI SDK language model; A database adapter with isolated transaction support for authenticated persistence
External service boundary
The adopter-selected AI model provider receives prompts and generates responses
Ownership boundary
You select and pay the model provider. Authenticated history stays in your database, and ejected chat pages become editable application code while streaming and data behavior remain packaged.
Real authenticated BTST AI Chat shell with an empty conversation-history sidebar, attachment control, and a product-context prompt ready to send.
The capture proves the shipped chat shell and prompt boundary; it deliberately does not fabricate a model response.

BTST supplies

  • Streaming chat APIs with typed tool, attachment, and lifecycle boundaries
  • Conversation and message models for authenticated history
  • SSR-aware conversation list and chat routes
  • Customizable chat pages, hooks, and prompt UI

You supply

  • An AI SDK model provider, credentials, usage policy, and provider billing
  • A database adapter with isolated transactions for authenticated history
  • Authorization rules for authenticated access, tools, and attachments
  • An upload implementation when file attachments are enabled

You own and customize

You select and pay the model provider. Authenticated history stays in your database, and ejected chat pages become editable application code while streaming and data behavior remain packaged.

Compatibility and dependencies

Maintained integrations
Next.js 15+ App Router · React Router v7 · TanStack Start
Requires
An AI SDK language model; A database adapter with isolated transaction support for authenticated persistence
External services
The adopter-selected AI model provider receives prompts and generates responses

From registration to result

The shipped workflow

This is the feature path BTST supplies—not a claim that your app needs no integration work.

  1. Choose a model

    Pass an AI SDK model and keep its credentials in your server environment.

  2. Set access

    Use authenticated persistence with typed rules or choose explicit stateless public mode.

  3. Stream

    Run prompts, tools, and optional attachments through the supplied chat route.

  4. Keep context

    Store identity-scoped conversations in your database when authenticated mode is enabled.

Continue your task

Move from evaluation to the right implementation boundary.