Give agents
a secure runtime
Ephemeral, isolated sandboxes designed for agent-generated code.
Run untrusted code safely
Spin up ephemeral microVMs for agent-generated code. Agents get full root inside the sandbox, so they can install packages, run Docker, and do anything else you'd do on a Linux box. Your core infrastructure and other workloads stay untouched.
Agent code runs in a dedicated VM, isolated from yourinfrastructure and from other sandboxes.
Inject credentials into outbound API requests from the sandbox, so your agent can call external services without secrets ever touching the runtime.
Use the Python or JS SDK with Deep Agents, another framework, or no framework at all.
.avif)
Sub-second starts
Spin up hundreds of sandboxes in parallel with one SDK call. Prewarming keeps p50 latency under 1.12s, so agents get an environment the moment they need one.
Launch fleets of sandboxes for evals, parallel agent runs, orRL training without rate limits or queueing.
Keep a pool of sandboxes ready to go so agents pick up anenvironment instantly instead of waiting for one to boot.
Define dependencies, CPU, and memory in a Docker image, then reuse it across sandboxes.
Built for long-running, statefulwork
Sessions run over WebSockets with streamed output, and state persists across threads. Sandboxes stay alive only as long as you need.
Set inactive TTLs so idle sandboxes shut down automatically, and set hard TTLs to cap total runtime.
Snapshot a running sandbox to capture its full state, then restore later to resume where you left off, or fork the snapshot into multiple sandboxes so an agent can branch and explore alternatives in parallel.
Open any port inside the sandbox and tunnel it to your local machine to preview a running app, hit an HTTP endpoint, orconnect to a service the agent spun up.
.avif)
Resources for LangSmith Sandboxes
FAQs for LangSmith Sandboxes
Sandboxes are isolated environments that run agent code without affecting your main infrastructure. Each one uses microVM isolation and is ephemeral by default. Learn more.
Bring your own Docker image or start from a template. Templates let you define container images, resource limits, volumes, and Auth Proxy configuration, then reuse them across sandboxes. Learn more.
The Auth Proxy injects credentials into outbound API requests from the sandbox, so your agent can call external services without secrets ever touching the runtime. Learn more.
No. Sandboxes are framework agnostic. They work with the Python and TypeScript LangSmith SDKs and integrate with Deep Agents, but you can use them with any framework or none at all. Learn about LangSmith Sandbox SDK.
Anything you can package in a Docker image runs inside a sandbox. The Python and TypeScript SDKs are available for creating and managing sandboxes from your code. Learn about LangSmith Sandbox SDK.
See our pricing page for more information, and find a plan that works for you.
Ready to ship agents that execute code?
Give your agents an isolated runtime without exposing your infrastructure. Spin one up in a single SDK call.