--- title: LangSmith Sandboxes: secure code execution environments... description: LangChain has released LangSmith Sandboxes in Private Preview, providing agents with isolated, secure environments to write and execute code. Each sandbox runs... canonical: https://daily.dev/posts/langsmith-sandboxes-secure-code-execution-environments-for-agents-uz5xaktf3 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: LangSmith Sandboxes: secure code execution environments for agents | daily.dev og:description: LangChain has released LangSmith Sandboxes in Private Preview, providing agents with isolated, secure environments to write and execute code. Each sandbox runs... og:url: https://daily.dev/posts/langsmith-sandboxes-secure-code-execution-environments-for-agents-uz5xaktf3 og:image: https://api.daily.dev/og/posts/Uz5xAKtF3.png og:image:alt: LangSmith Sandboxes: secure code execution environments for agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # LangSmith Sandboxes: secure code execution environments for agents **[Collections](https://daily.dev/sources/collections)** · 1 min read · 1 upvotes · 0 comments ## Summary LangChain has released LangSmith Sandboxes in Private Preview, providing agents with isolated, secure environments to write and execute code. Each sandbox runs in an ephemeral microVM-isolated environment, preventing untrusted agent-generated code from affecting the host system. Key capabilities include single-line SDK setup, bring-your-own Docker image support, sandbox templates, pooling and autoscaling, long-running WebSocket sessions, persistent state across interactions, and an auth proxy to keep secrets off the runtime. It integrates natively with LangSmith Deployment and the Deep Agents framework. Upcoming features include shared volumes, binary authorization, and full execution tracing. Access is currently via waitlist. ## Content LangChain has launched LangSmith Sandboxes, a new Private Preview feature that gives agents a secure environment to write and run code. The pitch is straightforward: agents become a lot more useful when they can actually execute code - analyzing data, calling APIs, running scripts. Sandboxes are designed to make that safe and easy to set up. ## How it works Each sandbox runs in an ephemeral microVM-isolated environment, so untrusted agent-generated code can't escape into the host system. Key features include: - Single-line SDK setup - Bring-your-own Docker image support - Sandbox templates - Pooling and autoscaling - Long-running WebSocket sessions - Persistent state across agent interactions - An auth proxy that keeps secrets off the runtime It integrates natively with LangSmith Deployment and the Deep Agents framework. ## What's coming Upcoming features include shared volumes across sandboxes, binary authorization, and full execution tracing inside the VM. ## Access Sandboxes are currently on a waitlist. LangChain says they'll be moving people through quickly - sign up or DM [@hwchase17](https://twitter.com/hwchase17) directly. --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#langchain](https://daily.dev/tags/langchain), [#langsmith](https://daily.dev/tags/langsmith) [View this post on daily.dev](https://daily.dev/posts/langsmith-sandboxes-secure-code-execution-environments-for-agents-uz5xaktf3) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"LangSmith Sandboxes: secure code execution environments for agents","url":"https://daily.dev/posts/langsmith-sandboxes-secure-code-execution-environments-for-agents-uz5xaktf3","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/langsmith-sandboxes-secure-code-execution-environments-for-agents-uz5xaktf3"},"datePublished":"2026-03-17T16:56:56.450Z","dateModified":"2026-06-04T02:13:56.978Z","description":"LangChain has released LangSmith Sandboxes in Private Preview, providing agents with isolated, secure environments to write and execute code. Each sandbox runs...","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/langsmith-sandboxes-secure-code-execution-environments-for-agents-uz5xaktf3","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,langchain,langsmith","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"LangSmith Sandboxes: secure code execution environments for agents"}]} ```