Automations
Islo automations are repeatable workloads that run in managed sandboxes. Use them when work should survive disconnects, run on a schedule, react to an external event, or be started by another system.
For AI agents, start with islo-labs/skills. The skills repo is the maintained, agent-readable reference for Islo automations, sandbox lifecycle, gateway integrations, SDK usage, and templates. It is the best way to teach Cursor, Claude Code, Codex, and other agents how to use Islo correctly.
Automation building blocks
Durable jobs
A job defines what to run and which sandbox it needs. A deployment creates a versioned job definition, and a run executes that version with parameters.
The standard manifest path is:
Common sections include:
[job]for name, version, and description[job.params.*]for parameter schema and validation[run]for timeouts, working directory, teardown behavior, and failure policy[run.sandbox]for image, CPU, memory, snapshot, init mode, and gateway profile[[run.tasks]]and[[run.tasks.steps]]for ordered commands inside the sandbox[schedule]for recurring runs
Use a gateway profile when an automation needs provider access. This keeps GitHub, Slack, model provider, and other secrets out of the sandbox environment by default.
Scheduled jobs
Use [schedule] in job.toml for recurring runs:
Deploying the job creates or updates its schedule:
Keep scheduled job tasks idempotent. Retries and repeated runs are part of the automation model.
Incoming webhooks
Incoming webhooks let external systems such as GitHub, Stripe, Slack, or your own service trigger sandbox actions. A webhook can:
- ensure a sandbox exists
- resume a paused sandbox
- pause or delete a sandbox
- deliver the request to a port inside a sandbox
- trigger job-oriented automation when supported by the API or CLI
For webhook configuration details, see Incoming Webhooks.
Agent guidance
When you want an agent to build or maintain Islo automations, point it at islo-labs/skills. The repository includes an Islo skill and plugin metadata that explain the current automation model, recommended CLI discovery commands, gateway credential patterns, and runnable-template pointers.
Recipes and examples are useful for humans looking at a specific pattern, but the skills repo should be the first link for agent setup and agent-authored automation work.