This quickstart walks you through your first Otto session. By the end, Otto is running in your project and ready to help you author, debug, and manage Dags. You can also optionally start local Airflow so Otto can query Dag runs, task logs, connections, and variables.
Otto requires an Astro account. Start a free trial if you don’t have one.
astro login.From your Astro project folder, run:
Otto opens an interactive terminal interface. The CLI handles authentication automatically.
You can also prompt Otto to start a local Airflow environment:
“Configure this project for standalone mode and start local Airflow.”
With Airflow running, Otto can use the af CLI to query Dag runs, task logs, connections, and variables on the live instance, and automatic Dag validation runs after each edit. See Local Airflow overview for the standalone vs Docker comparison.
Enter a prompt in the input area. To explore your project, try:
“Look at my Dags and summarize each one.”
Otto reads your Dag files, checks the running Airflow instance for metadata, and provides a summary of each Dag with its schedule, tasks, and dependencies.
“Check my Dags for deprecated patterns.”
Otto validates your code against your Airflow version.
“Why did my last Dag run fail?”
Otto checks task logs and run history to diagnose failures.
“Create a new Dag that pulls data from Snowflake and loads it into Postgres.”
Otto authors a Dag using your project’s conventions and connection IDs.
Otto persists session history automatically. To continue your most recent session:
To pick from a list of previous sessions in an interactive picker:
To open a specific session file:
Session files are stored as JSONL at ~/.astro/otto/sessions/.
When you launch Otto in an Astro project folder, it automatically detects:
.astro/ configuration. If Otto doesn’t find one, it falls back to the current working directory.astro dev start..astro/memory/ (shared project memory), ~/.astro/memory/<project-slug>/ (local project memory), or ~/.astro/memory/ (local user memory). See Memory.