Code Interpreter
Run untrusted code in isolated environments with real-time output streaming.
Give every agent its own machine. Spin up in 200ms, run code, tear down.
pip install leap0 | 1 | from leap0 import Leap0Client |
| 2 | |
| 3 | client = Leap0Client() |
| 4 | sandbox = client.sandboxes.create() |
| 5 | |
| 6 | try: |
| 7 | result = sandbox.process.execute( |
| 8 | command="echo Hello from Leap0", |
| 9 | cwd="/home/user", |
| 10 | timeout=30, |
| 11 | ) |
| 12 | print(result.exit_code) |
| 13 | print(result.stdout) |
| 14 | print(result.stderr) |
| 15 | finally: |
| 16 | sandbox.delete() |
| 1 | import Leap0Client from "leap0" |
| 2 | |
| 3 | const client = new Leap0Client() |
| 4 | const sandbox = await client.sandboxes.create() |
| 5 | |
| 6 | try { |
| 7 | const result = await sandbox.process.execute({ |
| 8 | command: "echo Hello from Leap0", |
| 9 | cwd: "/home/user", |
| 10 | timeout: 30, |
| 11 | }) |
| 12 | console.log(result.exitCode) |
| 13 | console.log(result.stdout) |
| 14 | console.log(result.stderr) |
| 15 | } finally { |
| 16 | await sandbox.delete() |
| 17 | await client.close() |
| 18 | } |
Turn any container image into a reusable template. Public registries, private ECR, GCP Artifact Registry, or Azure ACR.
Capture a point-in-time snapshot of any running sandbox, in-memory state and writable disk included. Restore it later into a brand new sandbox that picks up exactly where you left off.
Leap0 provides isolated sandboxes for code execution, agent workflows, browser automation, and desktop tasks. It is designed so LLM products can run real work without sharing state with other tenants.
Any Linux binary, any language, any framework. Each sandbox is a full microVM with its own kernel.
Sandboxes boot in around 200ms. Agents can start executing code almost instantly instead of waiting on heavy infrastructure boot time.
Yes. You can checkpoint configured environments and restore them later, which is useful for repeatable eval runs, warm developer environments, or agent jobs that need a prepared state.
Yes. Leap0 supports per-sandbox firewall controls so you can allow only the domains or ranges your workflow actually needs. You can also use transforms to inject or strip headers on a per-domain basis for credential brokering so secrets never enter the sandbox.
Every sandbox runs in its own Firecracker microVM with a dedicated Linux kernel. The VMM process is jailed with chroot, cgroup v2, seccomp filters, and unique UID/GID pairs.
Sandboxes currently run in the US. More regions are planned.
Leap0 is primarily offered as a fully managed service with the option to bring your own compute (BYOC). However, it can also be deployed on your own infrastructure. Contact our sales team for more information.