Anvia Docs

Start with a normal Anvia agent. Studio does not define agent behavior. It only runs and inspects agents you already built.

1. Install the Studio Package

pnpm add @anvia/core @anvia/openai @anvia/studio

2. Create a Studio Entry File

import { AgentBuilder, createTool } from "@anvia/core";
import { OpenAIClient } from "@anvia/openai";
import { Studio } from "@anvia/studio";
import { z } from "zod";

const client = new OpenAIClient({ apiKey });
const model = client.completionModel("gpt-5");

const getOrder = createTool({
  name: "get_order",
  description: "Read an order summary from application state.",
  input: z.object({
    id: z.string().describe("The order id to read."),
  }),
  output: z.object({
    id: z.string(),
    status: z.enum(["processing", "blocked", "shipped"]),
    notes: z.string(),
  }),
  async execute({ id }) {
    return {
      id,
      status: "blocked" as const,
      notes: "Payment review is complete, but allocation is still pending.",
    };
  },
});

const agent = new AgentBuilder("support-operations", model)
  .name("Support Operations")
  .description("Answers operational support questions.")
  .instructions("Use tools for private order data. Keep answers concise.")
  .tool(getOrder)
  .defaultMaxTurns(3)
  .build();

new Studio([agent]).start({ port: 4021 });

3. Start It

pnpm tsx studio.ts

Open http://localhost:4021/playground.

If you omit the port, Studio uses RUNNER_PORT and then falls back to 4021.

4. Check the Runtime

curl http://localhost:4021/health

{
  "status": "ok",
  "runner": {
    "id": "anvia-studio"
  }
}

5. Run Through the API

curl -X POST http://localhost:4021/agents/support-operations/runs \
  -H 'content-type: application/json' \
  -d '{"message":"What is happening with order ORD-1001?"}'

Studio returns the same kind of prompt response as agent.prompt(...).send().

Development Loop

Edit the agent, tools, instructions, or hooks.
Restart the Studio entry file.
Try prompts in the playground.
Inspect tool calls, output, sessions, and traces.