> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ai-stats.phaseo.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Build a durable agent loop in TypeScript

> Run a resumable agent loop on top of AI Stats Gateway with the TypeScript Agent SDK.

Use this recipe when you want more than a one-shot text request:

* multi-step tool loops
* local runtime tools
* resumable runs
* a single gateway-backed entrypoint for agent work

## 1. Install the SDKs

<CodeGroup>
  ```bash npm theme={null}
  npm install @ai-stats/sdk @ai-stats/agent-sdk
  ```

  ```bash pnpm theme={null}
  pnpm add @ai-stats/sdk @ai-stats/agent-sdk
  ```

  ```bash yarn theme={null}
  yarn add @ai-stats/sdk @ai-stats/agent-sdk
  ```

  ```bash bun theme={null}
  bun add @ai-stats/sdk @ai-stats/agent-sdk
  ```
</CodeGroup>

## 2. Define one small runtime tool

Keep the first tool deterministic and easy to inspect.

```ts theme={null}
import { defineTool } from "@ai-stats/agent-sdk";

export const lookupDocs = defineTool({
  id: "lookup-docs",
  description: "Look up internal docs by slug.",
  async execute(input: { slug: string }) {
    return {
      slug: input.slug,
      url: `https://docs.ai-stats.phaseo.app/v1/${input.slug}`,
    };
  },
});
```

## 3. Create the agent

```ts theme={null}
import { createAgent } from "@ai-stats/agent-sdk";
import { lookupDocs } from "./tools";

export const supportDocsAgent = createAgent({
  id: "support-docs-agent",
  model: "ai-stats/free",
  instructions: "Use tools when helpful and finish with a concise answer.",
  tools: [lookupDocs],
});
```

## 4. Use the gateway-backed adapter

```ts theme={null}
import {
  createGatewayAgentClient,
} from "@ai-stats/agent-sdk";
import { supportDocsAgent } from "./agent";

const result = await supportDocsAgent.run({
  input: "Find the docs page for presets and explain when to use them.",
  client: createGatewayAgentClient({
    clientOptions: {
      apiKey: process.env.AI_STATS_API_KEY!,
    },
  }),
});

console.log(result.output);
```

## 5. What persists between steps

Each completed step updates returned run state with:

* the run id
* the message history
* any returned tool calls
* any local tool results
* the final output when the run completes

If you want resumability across requests or processes, persist that returned value in your own application and pass it back into `continueRun()` later.

## 6. When to keep the first version simple

* one agent per workflow
* application-owned serialization before any cross-request resume flow
* a small tool list before generic tool registries
* one log line per run with the run id and gateway request id

## 7. When to move beyond this recipe

Move past the first durable loop when you need:

* approval pauses
* application-owned persistence for returned run state
* multiple agent definitions with shared runtime tools

At that point, keep the same gateway-backed adapter and evolve the store and orchestration around it.

## Related guides

* [TypeScript Agent SDK](../sdk-reference/typescript/agent-sdk.mdx)
* [Presets](../guides/presets.mdx)
* [Routing and fallbacks](../guides/routing-and-fallbacks.mdx)
* [Set up coding agents with SKILL.md](./coding-agents-skill-md.mdx)
* [Launch on the free router](./free-router-first-deploy.mdx)