TanStack Start
06 Persistence
Store TanStack Start conversation history with app storage or Anvia memory.
Persist conversation state in server code. Client components should call server routes or server functions.
1. Explicit Transcript Storage
import { Message } from "@anvia/core";
import { supportAgent } from "~/ai/support-agent";
import { conversations } from "~/db/conversations";
export async function runSupportTurn(input: {
conversationId: string;
message: string;
}) {
const history = await conversations.loadMessages(input.conversationId);
const response = await supportAgent
.prompt([...history, Message.user(input.message)])
.send();
await conversations.saveMessages(input.conversationId, [
...history,
...response.messages,
]);
return response;
}Call this helper from a server route or createServerFn(...).
2. Agent Memory
const agent = new AgentBuilder("support", model)
.memory(memoryStore, { savePolicy: "message" })
.build();
const response = await agent
.session(conversationId, { userId })
.prompt(message)
.send();Use memory when the route should not load and append messages manually.
3. Streaming Persistence
For streaming routes, wait for the terminal event in the client or use memory on the agent. Use an event store when you need replayable runtime events.
Next
Review deployment checks in Deploy. Related guides: Memory, Raw SQL, and Event Store.