✴️ E2B Cookbook

Example code and guides for building with E2B SDK.

Read more about E2B on the E2B website and the official E2B documentation.

Examples

Hello World guide

• TypeScript
• Python

Open-source apps

• E2B AI Analyst - analyze your data & create interactive charts
• E2B Fragments - prompt different LLMS to generate apps with UI
• E2B Surf - computer use AI agent powered by OpenAI

LLM providers

Provider	Topic(s)	Example	Python	TypeScript
OpenAI	Agents SDK	Agentic workflows running in E2B sandboxes	Python	-
	GPT-5.6	Data analysis and visualization of a CSV	Python	TypeScript
	GPT-5.6	Code interpreter and reasoning on image data	Python	TypeScript
	GPT-5.6	Code interpreter for ML on dataset	Python	TypeScript
	Codex CLI	OpenAI Codex, running inside a Sandbox	Python	TypeScript
Anthropic	Claude Opus 5	Code interpreter	Python	TypeScript
	Claude Code	Claude Code, running inside a Sandbox	Python	TypeScript
	Claude Managed Agents	Self-hosted worker running inside a Sandbox	Python	-
Meta	Muse Spark	Coding agent with E2B as its execution backend	Python	-
Mistral	Codestral	Code interpreter	Python	TypeScript
Groq	Llama 3	Code interpreter via function calling	Python	TypeScript
Fireworks AI	Qwen2.5-Coder-32B-Instruct	Code interpreter	Python	-
	Llama 3.1 405B, 70B, 8B	Code interpreter	Python	-
Together AI	Llama 3.1, Qwen 2, Code Llama, DeepSeek Coder	Code interpreter	Python	TypeScript
WatsonX AI	IBM Graphite, Llama, Mistral	Code interpreter	Python	TypeScript

AI frameworks integrations

Framework	Description	Python	TypeScript
🦜⛓️ LangChain	LangChain with Code Interpreter	Python	-
🦜🕸️ LangGraph	LangGraph with code interpreter	Python	-
CrewAI	CrewAI agent with sandboxed Python execution	Python	-
▲ Vercel AI SDK	Next.js + AI SDK + Code Interpreter	-	TypeScript
▲ Vercel AI SDK	AI SDK sandbox provider: sandboxed tools via restricted sessions, and harness coding agents (Claude Code, Codex) running inside E2B	-	TypeScript
▲ Vercel eve	Feedback analyst agent whose sandbox backend is E2B, publishing an HTML report from the sandbox	-	TypeScript
Flue	Feedback analyst agent running entirely inside an E2B sandbox, publishing an HTML report from the sandbox	-	TypeScript
Pi	Pi builds its own E2B code-interpreter extension in a sandbox, then uses it to analyze data	-	TypeScript
AgentKit	AgentKit Coding Agent	-	TypeScript
Sandbox Agent SDK	Run Sandbox Agent inside E2B and connect with the SDK	-	TypeScript
Stirrup	The lightweight framework for building agents	Python	-

Remote execution integrations

Integration	Description	Python	TypeScript
Crabbox	Warm one E2B sandbox, sync local changes, and rerun a test suite on the same lease	Python	-

Model Context Protocol (MCP)

Example	Description	TypeScript
MCP Client	Basic MCP client connection to E2B sandbox	TypeScript
MCP Custom Server	Connect to custom filesystem MCP server from GitHub	TypeScript
MCP Custom Template	Create custom E2B template with pre-installed MCP servers	TypeScript
MCP Research Agent	Research agent using arXiv and DuckDuckGo MCP servers	TypeScript
MCP Claude Code	Claude Code with MCP integration	TypeScript
MCP Browserbase	Web automation agent using Browserbase MCP server	TypeScript
MCP Groq Exa	AI research using Groq with Exa MCP server	TypeScript

Example use cases

• Upload dataset and analyze it with Llama 3.3 - Python
• Scrape Airbnb and analyze data with Claude Opus 5 and Firecrawl - TypeScript
• Visualize website topics with Claude Sonnet 5 and Firecrawl - Python
• Next.js app with LLM + Code Interpreter and streaming - TypeScript
• How to run a Docker container in E2B - Python/TypeScript
• How to run Playwright in E2B - TypeScript
• Map custom subdomains to your sandboxes - TypeScript
• Feedback analyst agent on Flue, publishing an HTML report from a sandbox - TypeScript
• Warm an E2B sandbox and rerun tests after adding a local regression case - Python

Running the examples as a test suite

Every example is exercised nightly against live E2B by tests/run-examples.ts: each one is uploaded into a fresh sandbox, installed with its own toolchain (npm, uv, Poetry, or nbconvert for notebooks) and run. An example passes if it exits 0.

npm install
npm test                      # all of them
npm test -- hello-world       # substring filter, one or a few

You need an E2B_API_KEY plus whichever provider key the examples you are running use - see .env.example. hello-world-js and hello-world-python need only the E2B key, so they are the ones to try first.

What counts as a failure. The suite checks the sandbox, not the model. A provider rate limit or an exhausted quota counts as OK, because the sandbox still built, installed and ran; non-deterministic model behaviour - no chart produced, a malformed tool call, generated code raising inside the sandbox - is reported as skipped. Real failures are the things that are actually broken: missing templates, dependency resolution, wrong entrypoints, auth, retired model ids, sandbox timeouts.

Some examples are deliberately not covered - they need a provider key this repo does not hold, a long-lived server the runner cannot assert on, or an upstream fix. Each exclusion is listed with its reason at the top of tests/run-examples.ts, so a gap is never silent.