Modal logo
FeaturedGetting started Hello, worldSimple web scraperServing web endpointsLarge language models (LLMs) Deploy an OpenAI-compatible LLM service with vLLMCut Ministral 3 cold start times by 10x with snapshotsMaximize tokens per second in batch processing with vLLMServe an ultra-low-latency chatbot with SGLangEfficient LLM Finetuning with UnslothRun a multimodal RAG chatbot to answer questions about PDFsFine-tune an LLM to replace your CEODeploy a stateless MCP with FastMCPImages, video, & 3D Edit images with Flux KontextFine-tune Wan2.1 video models on your faceRun Flux fast with torch.compileFine-tune Flux with LoRAAnimate images with LTX-VideoGenerate video clips with LTX-VideoRun Stable Diffusion with a CLI, API, and web UIAudio Deploy a Moshi voice chatbotStream transcripts at the speed of speech using Kyutai STTMake music with ACE-StepGenerate speech with ChatterboxRun high throughput batched transcription with WhisperFine-tune Whisper to recognize new wordsReal-time communication (WebRTC) Serverless WebRTCWebRTC quickstart with FastRTCComputational biology Fold proteins with Chai-1Build a protein-folding dashboardFold proteins with Boltz-2Modal Sandboxes Run a background coding agent with OpenCodeBuild a scalable AI coding platformRun a LangGraph agent's code in a secure GPU sandboxControl a sandboxed computer with an LLMBuild a stateful, sandboxed code interpreterRun Node.js, Ruby, and more in a SandboxRun a sandboxed Jupyter notebookReinforcement Learning Train a model to solve math problems using GRPO and verlTrain a model to solve coding problems using GRPO and TRLEmbeddings Embed millions of documents with TEITurn satellite images into vectors and store them in MongoDBParallel processing and job scheduling Deploy a Hacker News SlackbotRun a Document OCR job queueServe a Document OCR web appTraining models from scratch Train an SLM with early-stopping grid search over hyperparametersRun long, resumable training jobsHosting popular libraries YOLO: Fine-tune and serve computer vision modelsBlender: Build a 3D render farmStreamlit: Run and deploy Streamlit appsComfyUI: Run Flux on ComfyUI as an APISQLite: Publish explorable data with DatasetteAlgolia: Build docsearch with a crawlerConnecting to other APIs Discord: Deploy and run a Discord BotGoogle Sheets: Sync databases and APIs to a Google SheetOpenAI: Run a RAG Q&A chatbotTailscale: Add Modal Apps to your VPNPrometheus: Publish custom metrics with PushgatewayManaging data Mount S3 buckets in Modal appsBuild your own data warehouse with DuckDB, DBT, and ModalCreate a LoRA Playground with Modal, Gradio, and S3Miscellaneous
View on GitHub

Build a stateful, sandboxed code interpreter

This example demonstrates how to build a stateful code interpreter using a Modal Sandbox.

We’ll create a Modal Sandbox that listens for code to execute and then executes the code in a Python interpreter. Because we’re running in a sandboxed environment, we can safely use the “unsafe” exec() to execute the code.

Setting up a code interpreter in a Modal Sandbox 

Our code interpreter uses a Python “driver program” to listen for code sent in JSON format to its standard input (stdin), execute the code, and then return the results in JSON format on standard output (stdout).

We run this driver program in a Modal Sandbox.

We have to convert the driver program to a string to pass it to the Sandbox. Here we use inspect.getsource to get the source code as a string, but you could also keep the driver program in a separate file and read it in.

We then kick off the program with Sandbox.exec, which creates a process inside the Sandbox (see modal.container_process for details).

Running code in a Modal Sandbox 

Now we need a way to run code inside that running driver process. Our driver program already defined a JSON interface on its stdin and stdout, so we just need to write a quick wrapper to write to the remote stdin and read from the remote stdout.

Now we can execute some code in the Sandbox!

The Sandbox and our code interpreter are stateful, so we can define variables and use them in subsequent code.

We can also see errors when code fails.

Finally, let’s clean up after ourselves and terminate the Sandbox.