An operating system for AI agents

Maitento is an AI operating system. Everything an agent needs runs on Maitento: the model calls, conversations between agents, tool calls to the web and to your own APIs, memory, files and schedules. Your code stays small: deploy a folder, run a task, read the answer, from TypeScript, Python, C# or the mt command line.

Hello world in 60 seconds

1. Describe an agent and a task. Two small files, in a folder called maitento:

maitento/agents/greeter.mtr

// The model this agent runs on. See the names you can use with `mt aimodel-list`.
model = @ref("deepseek.deepseek-v4-flash")
prompt = "You are a friendly assistant. Keep every answer to one or two sentences."
summary = "A friendly assistant"

maitento/interactions/one-shot/hello.mtr

// A one-shot interaction: one agent, one task, one answer.
agent = {
  name = "Greeter"
  agent = @ref("greeter")
}
task = "Hello, how are you?"

2. Deploy them and run the task. Set MAITENTO_API_KEY to your API key and MAITENTO_NAMESPACE to a namespace name first.

TypeScriptPythonC#CLI

import { Maitento } from "@maitento/sdk";

// Reads your API key and namespace from MAITENTO_API_KEY and MAITENTO_NAMESPACE.
const mt = new Maitento();

// Send the agent and the interaction in ../maitento to Maitento.
await mt.deploy("../maitento");

// Start the "hello" interaction and wait for its answer.
const run = await mt.interactions.run("hello");
console.log(run.output);

from maitento import Maitento

mt = Maitento()  # reads MAITENTO_API_KEY and MAITENTO_NAMESPACE
mt.deploy("../maitento")

run = mt.interactions.run("hello")
print(run.output)

#:package Maitento.Sdk@26.10.0

using Maitento.Sdk;

// Reads your API key and namespace from MAITENTO_API_KEY and MAITENTO_NAMESPACE.
await using var mt = MaitentoClient.CreateFromEnvironment();

// Send the agent and the interaction in ../maitento to Maitento.
await mt.DeployAsync("../maitento");

// Start the "hello" interaction and wait for its answer.
var run = await mt.Interactions.RunAsync("hello");
Console.WriteLine(run.Output);

mt deploy ./maitento
mt interaction-run hello

3. Read the answer. The run comes back finished, with the agent’s reply in output:

I am well, thank you for asking. How may I assist you with your task today?

Next steps

• Get started takes you from signing up to your first agent, step by step.
• The tutorials build up, one idea at a time, from this hello to code pipelines and a small support desk.
• Sign up to get a tenant on the Free plan.