Skip to content
Try Hanzo
Language: English (United States)

Hanzo Auto

auto.hanzo.ai

Workflow automation in one binary

Step state is written down as it goes.React Flow · SSEpublished

A run kept as a recordstep 2 / 5 · GitHub

trigger
GitHub
Postgres
Slack
done
pod rescheduledrecord: resumes at step 3 · goroutine: starts over

A run held in a goroutinestep 2 / 5 · GitHub

trigger
GitHub
Postgres
Slack
done

draft

triggerGitHubPostgresSlack

published

triggerGitHubPostgres
POST trigger/v1/runs

React Flow · SSEpublished

trigger
GitHub
Postgres
Slack
done

record

  1. trigger
  2. GitHub
  3. Postgres
  4. Slack
  5. done

goroutine

  1. trigger
  2. GitHub
  3. Postgres
  4. Slack
  5. done

pod rescheduled

  • GoOne process
  • SQLitePer replica
  • /v1Flows and runs
  • ApacheSelf-hosted
containerauto:portstate.sqlite

GET /v1/pieces

  • Slack
  • GitHub
  • Notion
  • Gmail
  • Stripe
  • HubSpot
  • Jira
  • Linear
  • Discord
  • Airtable
  • Google Sheets
  • Postgres

connection

Hanzo IAMHanzo KMS

Some of what it connects

GET /v1/pieces

A run that survives the restart

  1. 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.

  2. GET /v1/pieces lists the connectors this build has. No plugin registry to reach at boot, so the version you deployed is the version that runs, offline and forever.

  3. POST to a trigger and a run starts. Or start one by hand against /v1/runs. Either way it is the same run object with the same history.

  4. The editor is React Flow, embedded in the binary, and it follows a run over a server-sent event stream — so the canvas you drew is the canvas you watch execute.

  5. Edit a flow freely; nothing changes for callers until you publish. What triggers fire is a published version, so editing in the afternoon does not change what runs overnight.

  6. A connection is a named credential the flow refers to. It is encrypted at rest through Hanzo KMS, and who may touch it is Hanzo IAM's answer, not a second login here.

Or run it yourself

One container, one port, a SQLite file for state. Nothing else to stand up first.

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

Get Auto

Workflow automations

License: Apache-2.0hanzoaiDeploy to Cloud