assistant-ui logo/Docs

Integrations

Third-party services and adapter recipes that plug into a working assistant-ui app.

Integrations are wiring guides for using third-party services with assistant-ui, plus canonical recipes for the adapter slots (persistence, attachments). They are distinct from runtimes, which are the React adapter packages (@assistant-ui/react-ai-sdk, @assistant-ui/react-langgraph, etc.) that connect the UI to a backend. An integration assumes you already have a working runtime and adds something on top.

Where integrations slot in

browser  ──►  your API route  ──►  LLM provider
                  │                    ▲
                  │                    │
       agent      │                    │  observability
       frameworks │                    │  proxies
       (e.g.      │                    │  (e.g. Helicone,
       Mastra)    │                    │   Langfuse)
                  ▼                    │
            run on the server,         │
            then forward calls   ──────┘
            to the provider

Integrations live on the server. Agent frameworks like Mastra take over the API route. Gateways swap the upstream provider URL. Observability logs or traces every call. Auth gates the route and scopes per-user data. Persistence and attachments are adapter recipes for storing chat data outside the default in-memory path.

Frameworks

Framework integrations that pair with assistant-ui at the API-route layer.

Vercel AI SDKThe canonical first-party adapter. Full setup lives under runtimes; this entry is the architectural pointer.MastraTypeScript agent framework. Routed through the AI SDK runtime, full-stack or separate server.

Tools

Pluggable tool catalogs and protocols.

Model Context Protocol (MCP)Connect any MCP server as a tool catalog through the AI SDK MCP client.

Gateways

OpenAI-compatible proxies that add catalog routing, fallback, BYOK, or self-hosting.

LLM gatewaysOpenRouter, Portkey, LiteLLM Proxy. Swap baseURL, route across providers.

Observability

Log, monitor, trace, and evaluate LLM calls. These pair with any runtime.

HeliconeObservability proxy. Drop-in baseURL swap that logs cost, latency, and prompts.LangfuseOpenTelemetry-based tracing and evals. Open source, self-hostable.LangSmithLangChain ecosystem tracing via wrapAISDK. Datasets and evals included.

Auth

Gate the chat route and scope thread data to the signed-in user. These pages are the non-cloud path; pair with custom thread persistence when you own the database.

ClerkHosted auth with a Next.js middleware. auth() returns userId; Clerk Orgs map to multi-tenant chat.better-authTypeScript-first, owns the user table and session. session.user.id is populated by default.Auth.js (next-auth)The OSS Next.js standard. Requires jwt/session callbacks to populate session.user.id.

For AssistantCloud users, cloud authorization handles the JWT exchange for Clerk, Auth0, Supabase, and Firebase without DB code.

Persistence

Store threads and messages outside AssistantCloud.

Custom thread persistenceWorked example: Postgres + Drizzle, RemoteThreadListAdapter, ThreadHistoryAdapter with withFormat.

Attachments

Upload chat attachments to object storage instead of inlining as data URLs.

Custom attachment uploadsProduction AttachmentAdapter with presigned URLs. Tabs for S3/R2, Vercel Blob, Uploadthing.

Don't see your service?

assistant-ui doesn't ship a guide for every tool, but most fit one of two patterns:

  • Routes through your AI SDK handler (agent frameworks, observability proxies, gateways): adapt the Mastra full-stack or Helicone proxy pattern using the service's own SDK.
  • Replaces the runtime entirely (custom backends): see custom backend.

If you build something useful, open an issue or post in Discord; the docs are open to contributions.

Pick a runtimeChoose the React adapter that matches your backend before adding integrations.Runtime conceptsArchitecture, adapters, threads, and stability across all runtimes.