--- title: LangChain product: vercel url: /docs/sandbox/ecosystem/langchain canonical_url: "https://vercel.com/docs/sandbox/ecosystem/langchain" last_updated: 2026-08-07 type: tutorial prerequisites: - /docs/sandbox/ecosystem - /docs/sandbox related: - /docs/sandbox - /docs/ai-gateway - /docs/cli - /docs/ai-gateway/authentication-and-byok/authentication - /docs/sandbox/sdk-reference summary: Give a LangChain agent a tool that executes model-generated code in an isolated Vercel Sandbox, with models served by AI Gateway. install_vercel_plugin: npx plugins add vercel/vercel-plugin --- # LangChain This guide shows how to give a [LangChain](https://js.langchain.com) agent a tool that executes code in [Vercel Sandbox](/docs/sandbox), so model-generated code runs in an isolated microVM instead of on your host. Model requests route through [AI Gateway](/docs/ai-gateway). ## Related pages > **For AI agents:** Follow these links to understand how this page connects to the rest of the Vercel ecosystem. For the full cross-link map (inbound, outbound, prerequisites, and semantic neighbors), see the .graph.md link below. - [Run Python code securely with AI SDK and Vercel Sandbox](https://vercel.com/kb/guide/python-ai-sdk-vercel-sandbox) — Add an \\`executeCode\\` tool to your AI SDK agent with the \\`ai-sdk-tool-code-execution\\` package to run Python 3.13 insi - [Running OpenCode securely with the Vercel Sandbox](https://vercel.com/kb/guide/running-opencode-securely-with-the-vercel-sandbox) — Run OpenCode in an isolated Vercel Sandbox MicroVM with controlled egress, using the SDK to restrict network access so t - [Safely running AI generated code in your Next.js application](https://vercel.com/kb/guide/running-ai-generated-code-sandbox) — How to execute untrusted, AI‑generated code from a Next.js app using Vercel Sandbox, an isolated, ephemeral environment. - [Building an agent with OpenAI Agents SDK and Vercel Sandbox](https://vercel.com/kb/guide/building-an-agent-with-openai-agents-sdk-and-vercel-sandbox) — Learn how to build an agent with with OpenAI Agents SDK and Vercel Sandbox - [Using Vercel Sandbox to run Claude’s Agent SDK](https://vercel.com/kb/guide/using-vercel-sandbox-claude-agent-sdk) — Learn how to deploy Claude's Agent SDK in Vercel Sandbox for secure and isolated execution of AI-powered code generation - [LangChain with AI Gateway](https://vercel.com/docs/ai-gateway/ecosystem/framework-integrations/langchain) — Learn how to integrate Vercel AI Gateway with LangChain to access multiple AI models through a unified interface. - [AgentEnv by Scale AI](https://vercel.com/docs/sandbox/ecosystem/agentenv) — Run evaluations with AgentEnv by Scale AI using separate Vercel sandboxes for the environment and agent. - [Deep Agents CLI with AI Gateway](https://vercel.com/docs/ai-gateway/coding-agents/deepagents) — Connect Deep Agents CLI to AI Gateway with the Vercel CLI or a TOML provider and model profiles. Full cross-link map for this page: [/docs/sandbox/ecosystem/langchain.graph.md](/docs/sandbox/ecosystem/langchain.graph.md) > **💡 Note:** You need a [Vercel account](https://vercel.com/signup), [Vercel > CLI](/docs/cli), Node.js 22 or later, and an [AI Gateway API > key](/docs/ai-gateway/authentication-and-byok/authentication). ## Getting started - ### Create a new project Create a new directory for your project and initialize it: ```bash filename="terminal" mkdir langchain-sandbox cd langchain-sandbox npm init -y ``` - ### Install dependencies Install LangChain, the Anthropic and OpenAI provider packages, and the Sandbox SDK: **pnpm** ```bash pnpm i langchain @langchain/core @langchain/anthropic @langchain/openai @vercel/sandbox zod ``` **yarn** ```bash yarn add langchain @langchain/core @langchain/anthropic @langchain/openai @vercel/sandbox zod ``` **npm** ```bash npm i langchain @langchain/core @langchain/anthropic @langchain/openai @vercel/sandbox zod ``` **bun** ```bash bun add langchain @langchain/core @langchain/anthropic @langchain/openai @vercel/sandbox zod ``` - ### Configure authentication Link the project to Vercel and pull your development environment. This creates a `.env.local` file with a `VERCEL_OIDC_TOKEN`, which authenticates the Sandbox SDK: ```bash filename="terminal" vercel link vercel env pull ``` Create an AI Gateway API key, then add it to `.env.local`: ```bash filename=".env.local" AI_GATEWAY_API_KEY=your_ai_gateway_api_key ``` > **💡 Note:** For other Sandbox authentication methods, see > [Authentication](/docs/sandbox/sdk-reference#authentication) in the SDK reference. - ### Create your agent Create a new file called `index.ts` with the following code: ```typescript filename="index.ts" import * as z from 'zod'; import { createAgent, tool } from 'langchain'; import { ChatAnthropic } from '@langchain/anthropic'; import { Sandbox } from '@vercel/sandbox'; const sandbox = await Sandbox.create({ timeout: 300_000 }); try { const runCode = tool( async ({ code }) => { const result = await sandbox.runCommand('node', ['-e', code]); return result.exitCode === 0 ? await result.stdout() : `Command failed: ${await result.stderr()}`; }, { name: 'run_code', description: 'Run Node.js code in an isolated Vercel Sandbox and return its output.', schema: z.object({ code: z.string().describe('Node.js code to execute'), }), }, ); const model = new ChatAnthropic({ model: 'anthropic/claude-opus-5', apiKey: process.env.AI_GATEWAY_API_KEY, anthropicApiUrl: 'https://ai-gateway.vercel.sh', }); const agent = createAgent({ model, tools: [runCode] }); const result = await agent.invoke({ messages: [ { role: 'user', content: "Compute the SHA-256 hex digest of the exact string 'vercel sandbox' with Node.js, then report the digest.", }, ], }); console.log(result.messages.at(-1)?.content); } finally { await sandbox.stop(); } ``` The `timeout` value bounds each sandbox session to five minutes. Model calls run outside the VM, and a later `sandbox.runCommand()` can resume a new session after the previous one times out. The session timeout doesn't bound the overall agent loop. Use an application deadline and cancellation strategy to bound the full loop, including model requests and tool submissions. A command's `timeoutMs` (or Python `kill_after`) bounds that command separately. The `finally` block stops the current session when the loop finishes or throws; coordinate cancellation with in-flight tool calls before cleanup so they don't resume another session. The following code: - Creates a sandbox that the agent reuses across tool calls - Defines a `run_code` tool that executes code with [`sandbox.runCommand()`](/docs/sandbox/sdk-reference#sandboxruncommand) - Points the Anthropic chat model at AI Gateway, authenticated with your Vercel credentials - Passes the tool to `createAgent`, which runs the tool-calling loop The example uses an Anthropic model. To use an OpenAI model instead, import `ChatOpenAI` from `@langchain/openai` and point it at the same gateway: ```typescript filename="index.ts" import { ChatOpenAI } from '@langchain/openai'; const model = new ChatOpenAI({ model: 'openai/gpt-5.6-sol', apiKey: process.env.AI_GATEWAY_API_KEY ?? process.env.VERCEL_OIDC_TOKEN, configuration: { baseURL: 'https://ai-gateway.vercel.sh/v1' }, }); ``` Any [AI Gateway model](/docs/ai-gateway/models-and-providers) works the same way. - ### Run the agent Run your agent with the environment variables from `.env.local`: ```bash filename="terminal" npx tsx --env-file=.env.local index.ts ``` The agent writes Node.js code, executes it in the sandbox, and reports the digest. --- [View full sitemap](/docs/sitemap) If you encounter incorrect information, can’t find what you need, need a capability Vercel doesn’t currently offer, or have any other feedback to report, please do it by following the instructions at https://vercel.com/feedback.md.