Welcome to Astro AI
Deploy and run AI agents with agent-native infrastructure
Get started
Welcome to Astro AI
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, create an agent, and run locally in three steps
Make your agent discoverable
Describe your agent with an AGENT.md file for discovery and display
Publish to registry
Log in and push your agent to the Astro AI registry (requires account)
Authentication
Log in with ast login and manage credentials
Concepts
- Astropods Spec — Declarative YAML format (
astropods.yml) that describes an agent’s topology: container, models, knowledge stores, tools, and ingestion. See Astropods Spec. - Agent Card — A Markdown file with YAML frontmatter (
AGENT.md) that describes what an agent does, who built it, and what it connects to. See Make your agent discoverable. - Agent — A deployable unit defined by an
astropods.ymlspec: container image, models, knowledge stores, tools, and integrations. - Registry — Astro AI registry where agent images and spec artifacts are published.
Next steps
Create and run an agent
Follow Your first project: ast create hello-astro, then cd hello-astro && ast dev.
