Run agents in sandboxes Ship what they build

An AI sandbox is a separate place for an agent to run code, use tools, and work with files. Lizard Sandboxes let agents build, test, and debug in the cloud without running that code on your computer.

Sign in to Lizard, choose a project, and create a sandbox from a ready-made template. Choose base for shell tasks, codex for coding tasks, or interpreter for Python, then select a size and region.

Yes. Run Python scripts with the interpreter template, or use shell commands to run tools and tests. Read command output and save results to files. Each command starts a new process.

In our 12 October 2026 test, the median time from the create request to the first Python output was 228 ms over 300 starts (base template, Small size, us-east-1). E2B took 264 ms, Daytona 819 ms and Modal 929 ms in the same test. Results vary with the template, size, region and free capacity.

Lizard Sandboxes run as Firecracker microVMs, each with its own kernel. Give the agent only the credentials and access its task needs.

You choose the lifetime when creating a sandbox, including no automatic expiry for longer tasks. A sandbox stops at its deadline even if a command is running. Commands do not extend the deadline, and idle time does not stop it early.

Yes. Attach Persistent Volumes at /workspace to keep files after a sandbox stops and reuse them in later runs. A volume connects to one sandbox at a time. Storage stays on one node, so export files you need to protect against node loss.

Yes. With access to your project, an agent can deploy apps and databases through Lizard CLI. They run as separate resources on Lizard and keep running after you stop or delete the sandbox.

Yes. Create a separate sandbox for each task so agents can run commands and tests at the same time. The trial runs up to 5 Sandboxes at once and Pro up to 100. Enterprise has no limit on how many run at once, so you can scale to thousands.

The Small size costs $0.0162/hour for 2 vCPU and 4 GB RAM. For the same 2 vCPU and 4 GB, E2B and Daytona charge $0.1656/hour and Modal $0.2380/hour (rates checked on 20 October 2026). Billing runs by the second while the sandbox runs, including idle time. CPU and RAM are included, along with 2 TB of sandbox egress per account over a rolling 30 days. A successful pause stops compute charges; Persistent Volumes storage is billed separately. Older sandboxes without a size keep their original usage-based billing.

Yes. Pro starts with a 7-day trial and $5 in trial credits, and Sandboxes run on it, up to 5 at once. You need a card to start, and we charge nothing during the trial. After it, Pro costs $19/month with $19 in monthly credits included. Once you use your credits, pay as you go.