Stately Agent

The logic layer for AI agents.

Build agents as state machines to control exactly what the agent can do. The machine owns control flow; the model only ever picks a legal event. Testing, inspection, and visualization fall out for free.

Stately Agent adds model requests and decisions to XState. The state machine defines what the agent can do. Your application chooses the model, runs the requests, and stores the state.

Any agent workflow or loop can be modeled as a state machine. Model calls and tools run as effects inside it. The model proposes an event. The machine decides whether it is allowed and what happens next.

Stately Agent 2 is in alpha. APIs may change before the stable release.

Documentation · Examples · XState

Three ways to start

• Author a new agent. Build a machine from states, decisions, and typed requests; run it locally with runAgent, test it with no API key, then use it in any framework or runtime with zero machine changes. See the Quickstart and Use in any stack.
• Retrofit an existing agent. Turn a while loop into a machine: your SDK calls, tools, and retry code become the executors; the machine replaces only the control flow. See Migrating from a loop.
• Copy a known pattern. ReAct, reflection, plan-and-execute, RAG, supervisor, and more, each a single runnable file you lift in 60 seconds. See Agent patterns.

Install

pnpm add @statelyai/agent@alpha xstate@alpha zod ai@^6 @ai-sdk/openai@^3

Node 22.18 or newer is required. The package is ESM-only; the library targets XState v6 alpha and stays compatible with XState v5. Provider packages must match your ai major: @ai-sdk/openai@^3 pairs with ai@^6 (a bare @ai-sdk/openai resolves to @latest, which can mismatch the ai peer).

Quick start

This agent reviews refund requests. The model may propose an automatic refund, but the state machine owns the $100 limit.

import { openai } from "@ai-sdk/openai";
import { runAgent, setupAgent } from "@statelyai/agent";
import { createAiSdkExecutors, defineModels } from "@statelyai/agent/ai-sdk";
import { z } from "zod";

const models = defineModels({
  fast: openai("gpt-5.4-mini"),
});

const agentSetup = setupAgent({
  models,
  context: z.object({
    request: z.string(),
    amount: z.number(),
  }),
  input: z.object({
    request: z.string(),
    amount: z.number(),
  }),
  output: z.object({
    outcome: z.enum(["refunded", "review"]),
  }),
  events: {
    AUTO_REFUND: {},
    REVIEW: z.object({ reason: z.string() }),
  },
});

const refundMachine = agentSetup.createMachine({
  context: ({ input }) => input,
  initial: "deciding",
  states: {
    deciding: {
      invoke: {
        src: "agent.decide",
        input: ({ context }) => ({
          model: "fast",
          system: "Choose AUTO_REFUND for eligible requests. Otherwise choose REVIEW.",
          prompt: `${context.request}\nAmount: $${context.amount}`,
          allowedEvents: ["AUTO_REFUND", "REVIEW"],
        }),
      },
      on: {
        AUTO_REFUND: ({ context }) => (context.amount <= 100 ? { target: "refunded" } : undefined),
        REVIEW: { target: "review" },
      },
    },
    refunded: {
      type: "final",
      output: () => ({ outcome: "refunded" }),
    },
    review: {
      type: "final",
      output: () => ({ outcome: "review" }),
    },
  },
});

const result = await runAgent(refundMachine, {
  input: {
    request: "I was charged twice for the same order.",
    amount: 75,
  },
  executors: createAiSdkExecutors({ models }),
});

if (result.status === "done") {
  console.log(result.output);
}

When the machine reaches refunded, the result is:

{ outcome: 'refunded' }

The model chooses between the events allowed in deciding. The AUTO_REFUND transition only works when the amount is at most $100. If the model chooses it for a larger amount, the guard rejects the choice and the decision is tried again.

The state machine

The example has one model decision and two final outcomes. Real machines can add approval states, retries, parallel work, child agents, and long-running waits without changing how the control flow is represented.

Core concepts

• Machines own control flow. States, events, transitions, and guards define what can happen.
• Models make bounded decisions. agent.decide asks a model to choose one of the events accepted by the current state.
• Requests are typed. Inputs, outputs, context, and events use Standard Schema. Zod works out of the box.
• Your code runs the model. runAgent accepts executor functions. The example uses the Vercel AI SDK adapter, but the machine does not depend on a provider.
• Snapshots can be stored. An agent can stop for human input, save its XState snapshot, and resume later in another process.
• Machines can be checked without model calls. Lint their structure, simulate scripted decisions, and explore paths without an API key.
• Agents are XState machines. Guards, actors, parallel states, inspection, testing, and visualization work as usual.

Examples

• Twenty Questions shows a model choosing legal events in a loop.
• Go Fish pits a model against a human while the machine enforces hidden-information game rules.
• Human in the loop pauses, stores a snapshot, and resumes after review.
• Ticket triage returns structured data from a model request.
• JSON agent runs a machine defined as data.

See all examples.

Learn more

• Machines
• Text requests
• Decisions
• Human in the loop
• Testing and verification
• Running on different hosts
• Use in any stack
• Agent patterns
• Migrating from a loop