A run that survives the restart
A run is a record, not a goroutine. Step state is written down as it goes, so a crash, a deploy or a rescheduled pod resumes where it stopped rather than starting over or losing the run.
Paste and ship
Paste this into any agent. It reads the skill manifest and calls Auto from there.
Agent prompt
Read https://hanzo.ai/skill.md and use Hanzo Auto in my project. Start with: hanzo auto flows list
GoOne process
SQLitePer replica
/v1Flows and runs
ApacheSelf-hosted
Some of what it connects
Slack
GitHub
Notion
Gmail
Stripe
HubSpot
Jira
Linear
Discord
Airtable
Google Sheets
Postgres
Open source royalty
20% to the author of the code that runs
Verify that you own a repository, and every org that deploys a project built from it pays you 20% of its metered spend, accrued each period.
Or run it yourself
One container, one port, a SQLite file for state. Nothing else to stand up first.