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 OpenCode in a Modal Sandbox

This example demonstrates how to run OpenCode remotely and connect to it from your local terminal or browser.

Combine self-hosted OpenCode with serving a big, smart model on Modal and you’ve got “coding agents at home”!

Coding agents are most useful when they have context and tools. By default, this script clones the Modal examples repo and gives the agent access to your Modal credentials, so it can run and debug examples (including this one!). Meta.

A screenshot of the OpenCode Web UI showing this coding agent running its own code

Set up OpenCode on Modal 

First, we define a Modal container Image with OpenCode installed.

Clone a GitHub repository 

Next, we clone the code we want the agent to work on. The repository is cloned into the container image at build time, so it’s available when the Sandbox starts.

Grant Modal credentials 

Since the agent is working with Modal code, we also make it easy to provide Modal access. Examples in this repo should run with nothing more than modal installed — except for a few that use fastapi.

Start the Sandbox 

Now, we create a Modal Sandbox to run our coding agent session. This Sandbox has our environment Image and a password for authentication.

We open up the OPENCODE_PORT so that the server can be accessed over the Internet.

OpenCode is truly open — there are many interfaces to the underlying coding agent server. Here we print information for:

  • directly accessing the underlying Modal Sandbox for debugging or “pair coding” with the agent
  • accessing the Web UI from a local browser (with authentication!)
  • accessing the TUI from your local terminal

The server is secured via a password in a Modal Secret. You can create one by heading to the Secrets Dashboard and creating a new “Custom” Secret. Use OPENCODE_SERVER_PASSWORD as the key and the password as the value.

The CLI will also give you a helpful one-liner you can use to recover the password with your Modal credentials in case you forget it.

Putting it all together 

Command-line options 

This script supports configuration via command-line arguments. Run with --help to see all options.

To grant the agent the same GitHub permissions you have, you can pass a GitHub personal access token. If you use the gh CLI, you can use shell command substitution to pass your current auth: