FreestyleAI Integrations
Langgraph JS
Code execution for Langgraph in JavaScript
You are viewing legacy Freestyle documentation. See the new documentation for the latest guides and API reference.
Install the required dependencies
npm install freestyle-sandboxes @langchain/langgraph @langchain/core @langchain/openaiThis walkthrough uses @langgraph/openai, however these exact steps should work for any of the langgraph providers like
@langgraph/anthropic
Get your Freestyle API Key from the Freestyle Dashboard
Set up the Code Executor
import { executeTool } from "freestyle-sandboxes/langgraph";
const codeExecutor = executeTool({
apiKey: process.env.FREESTYLE_API_KEY!,
});You can also pass in any nodeModules, environment variables, timeout, or network restrictions you need.
import { executeTool } from "freestyle-sandboxes/langgraph";
const codeExecutor = executeTool({
apiKey: process.env.FREESTYLE_API_KEY!,
nodeModules: {
mathjs: "14.3.1",
},
envVars: {
MY_SUPER_SECRET_KEY: "1234567890",
},
});Set up the Langgraph SDK Agent
const model = new ChatOpenAI({ model: "gpt-4o" });
const agent = createReactAgent({
llm: model,
tools: [codeExecutor],
});Invoke the Agent
const result = await agent.invoke({
messages: [
{ role: "user", content: "What is the factorial of 13 divided by 55^2" },
],
});
console.log(result.messages.at(-1)?.content);🚀 Your AI can now execute code