API & SDK Quickstart
Create and monitor your first cloud agent run via the Oz API or SDK in ~5 minutes.
The Oz API lets you run and manage cloud agents from anywhere — CI/CD pipelines, backend services, scripts, or custom tooling — without the Warp desktop app. This quickstart walks you through creating your first run and checking its status.
Watch this short demo of how the REST API can power agent-backed apps like PowerFixer, an issue triage bot built by the Warp team:
Prerequisites
A Warp API key - In the Warp app, click your profile photo, then go to Settings > Platform to create a key and copy the raw value. See API Keys for step-by-step instructions.
An Oz cloud environment - Agents run inside a configured environment that includes repos and other dependencies. If you don't have an environment yet, follow the Cloud Agents Quickstart first.
1. Set your API key
Export your API key so the API can authenticate your requests automatically — all commands in this guide reference the WARP_API_KEY environment variable.
Replace wk-... with the key you created earlier.
2. Create your first run
Submit a prompt to start an agent run:
Replace <ENV_ID> with your environment ID. Find it with oz environment list on the Oz CLI or in the Oz web app.
Prefer typed requests? The official Python SDK and TypeScript SDK wrap the same API with typed models, retries, and error handling.
The API returns a run_id immediately. The agent starts asynchronously — you can check its status at any time using the run ID.
3. Check run status
Fetch the current state of the run with the following command. Replace <RUN_ID> with the run_id from step 2.
The state has the following possible values:
QUEUED- The run is waiting to start.INPROGRESS- The agent is actively running.SUCCEEDED- The run completed successfully.FAILED- The run encountered an error. Check thestatus_messagefield in the response for details.
These are the most common states. See the full API reference for all possible values.
To list all recent runs:
4. View the results
Once the run reaches SUCCEEDED, the response includes a session_link — a direct URL to the full run transcript, including commands executed, files changed, and agent output.
You can also view and manage all runs in the Oz dashboard.
Next steps
Read the full API reference - Oz API documents all endpoint parameters, query filters, and response schemas.
Explore the SDKs - Python SDK and TypeScript SDK include typed request/response models, retries, and error handling.
See a real-world example - Demo: Sentry monitoring with SDK shows how to build a webhook handler that triggers agents from production errors.
Schedule and automate - See Scheduled Agents Quickstart to run agents on a cron, or Integrations Quickstart to trigger agents from Slack or Linear.
Last updated
Was this helpful?