Everything dagweave does.

Drag steps onto a canvas and wire up the dependencies. Retries, timeouts and node selectors are fields on the step, edited in a form.

Pull manifests from a GitHub repo, a live cluster through the connector, or a paste. Retry strategies and artifact repository refs come in intact.

S3, Postgres, kubectl, Helm, docker builds, LLM calls, ready to drop on the canvas. Starter blueprints too, plus a marketplace for templates your own team writes.

One helm install per cluster, and it ships production-ready. Authors dispatch runs to it without a kubeconfig of their own.

No cap on how many clusters you enroll, and clusters never count toward the bill.

Every connection the connector opens goes outward. Your firewall rules stay as they are. Runs can get their own namespace and service account, and nothing of yours is left standing on the cluster.

Start a run from a button, a schedule, a GitHub push, an SNS topic or a signed webhook. Status comes back onto the canvas you built it on, node by node.

The file in your repo is the file your cluster runs. Stop using dagweave and it keeps running.

A read-only HTTP API for runs, workflows and the audit log, with scoped per-user tokens. An MCP server runs on the same routes, and the assistant in your editor can pull a failed run itself.

Shared workspaces and single sign-on over SAML or OIDC. Put people in groups, grant a group one workflow at a time, and scope what their runs can touch on your cluster.