Get started

Welcome to Astro AI

Deploy and run AI agents with agent-native infrastructure

View as Markdown

Astro AI is a platform for deploying and running AI agents. It provides agent-native infrastructure including models, knowledge bases, tool integrations, and observability. Agents are defined with a declarative spec, built and pushed with the CLI, and deployed through the API or dashboard.

What you can do

Install the CLI

Download and install the ast CLI for your platform

Your first project

Install the CLI, log in, create an agent, run locally, and push in five steps

Authentication

Log in with ast login and manage credentials

API reference

List agents, register and push builds, and manage deployments via the API

Concepts

  • Agent — A deployable unit defined by an astro.yml spec: container image, models, knowledge stores, tools, and integrations.
  • Registry — OCI registry where agent images and spec artifacts are published (e.g. ghcr.io).
  • Account — Your team or org on Astro AI; agents are scoped to an account (account/agent-name).
  • Push — Pushing an agent (and optionally assigning a semver version) makes it available in your account and the public catalog.

Next steps

1

Install the CLI

Run curl -fsSL https://astropod.ai/install | sh or see Install the CLI.

2

Log in

Run ast login and complete the browser flow to authenticate.

3

Create and run an agent

Follow Your first project: ast create hello-astro, then cd hello-astro && ast dev.

4

Push

Run ast push to push your agent to the Astro AI registry.