Skip to main content
Sandboxes provide isolated compute environments for running untrusted code, agent tools, evaluations, and reinforcement learning (RL) workloads. Create an environment, run commands, work with files, and collect results through the Python or TypeScript software development kit (SDK). Sandboxes run on serverless capacity that CoreWeave operates, with no cluster to provision.
Serverless Sandboxes is generally available, and usage is billed. Access is enabled per organization. To request access for your organization, contact support.

​
Get started

Run your first sandbox

Authenticate and run a command with Python or TypeScript.

Run coding agents

Choose an integration for interactive coding or autonomous workers.
Connect Claude Code, Claude Managed Agents, or Devin Outposts to sandbox workspaces. For your own application, explore the Python client and TypeScript SDK. Use sandboxes with Harbor, or explore the Sandbox recipes for runnable warm pool and RL training examples.

​
Configure your sandboxes

Choose the features your workload needs:
  • Configure execution. Choose your image, CPU, memory, and lifetime with sandbox configuration.
  • Attach storage. Use volumes for scratch space.
  • Expose a service. Give a sandbox application a public address with public endpoints.
  • Use GPUs. Request GPU sandboxes. GPU sandboxes require separate access.
Last modified on September 30, 2026