Automations and the public API are the only sanctioned channels for programmatic use of Replicas. Driving the dashboard, Slack, Linear, GitHub, or CLI from scripts is prohibited under our Terms of Service.
How it works
Each automation has:- A prompt the agent will receive when the automation runs.
- One or more repositories (or a repository set) the agent will work against.
- One or more triggers that decide when the automation fires.
Triggers
Two trigger types are supported today:Cron triggers
Run an automation on a recurring schedule defined by a standard cron expression. The minimum interval is 60 minutes between runs.GitHub triggers
Run an automation in response to events from your connected GitHub repositories. For example, when a pull request opens, when a workflow run finishes, or when an issue is filed. You can optionally filter a GitHub trigger to a specific subset of repositories.Plan availability and limits
| Plan | Max automations | Org executions / hour | Per-automation executions / hour | Min cron interval |
|---|---|---|---|---|
| Hobby | Not available | — | — | — |
| Developer | 5 | 20 | 5 | 60 minutes |
| Team | Unlimited | Unlimited | Unlimited | 60 minutes |
| Enterprise | Unlimited | Unlimited | Unlimited | 60 minutes |
Reliability
Automations include a circuit breaker: if an automation fails 5 times in a row, it is automatically disabled to prevent runaway behavior. You can re-enable it from the dashboard once the underlying issue is fixed. Every execution is recorded with its status (pending, creating, running, completed, or failed) and any error message.