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

Run Anthropic’s computer use demo in a Modal Sandbox

This example demonstrates how to run Anthropic’s Computer Use demo in a Modal Sandbox.

Sandbox Setup 

All Sandboxes are associated with an App.

We start by looking up an existing App by name, or creating one if it doesn’t exist.

The Computer Use quickstart provides a prebuilt Docker image. We use this hosted image to create our sandbox environment.

We’ll provide the Anthropic API key via a Modal Secret which the sandbox can access at runtime.

Now, we can start our Sandbox. We use modal.enable_output() to print the Sandbox’s image build logs to the console. We’ll also expose the ports required for the demo’s interfaces:

  • Port 8501 serves the Streamlit UI for interacting with the agent loop
  • Port 6080 serves the VNC desktop view via a browser-based noVNC client

After starting the sandbox, we retrieve the public URLs for the exposed ports.

We can check on each server’s status by making an HTTP request to the server’s URL and verifying that it responds with a 200 status code.

You can now open the URLs in your browser to interact with the demo! Note: The sandbox logs may mention localhost:8080. Ignore this and use the printed tunnel URLs instead.

When finished, you can terminate the sandbox from your Modal dashboard or by running Sandbox.from_id(sandbox.object_id).terminate(). The Sandbox will also spin down after one hour.