Agent bootstrapping

Bootstrapping is the first‑run ritual that prepares an agent workspace and collects identity details. It happens after onboarding, when the agent starts for the first time.

What bootstrapping does

On the first agent run, OpenClaw bootstraps the workspace (default

):

• Seeds
  text

  Copy

  AGENTS.md
  ,
  text

  Copy

  BOOTSTRAP.md
  ,
  text

  Copy

  IDENTITY.md
  ,
  text

  Copy

  USER.md
  .
• Runs a short Q&A ritual (one question at a time).
• Writes identity + preferences to
  text

  Copy

  IDENTITY.md
  ,
  text

  Copy

  USER.md
  ,
  text

  Copy

  SOUL.md
  .
• Removes
  text

  Copy

  BOOTSTRAP.md
  when finished so it only runs once.

For embedded/local model runs, OpenClaw keeps

out of the privileged system context. On the primary interactive first run, it still passes the file contents in the user prompt so models that do not reliably call the tool can complete the ritual. If the current run cannot safely access the workspace, the agent gets a limited bootstrap note instead of a generic greeting.

Skipping bootstrapping

To skip this for a pre-seeded workspace, run

.

Where it runs

Bootstrapping always runs on the gateway host. If the macOS app connects to a remote Gateway, the workspace and bootstrapping files live on that remote machine.

Related docs

• macOS app onboarding: Onboarding
• Workspace layout: Agent workspace