App Store template
OpenHands icon

OpenHands

AI software development agent web app for editing code, running commands, and automating development tasks.

Launch in your Sealos workspace.

OpenHands template preview
Template previewFull screenshot
Template deployments
12 on Sealos
Deployment
Your own instance
Category
AI

About this template

Overview

OpenHands is an AI software development agent web application. This template deploys the OpenHands web UI on Sealos Cloud with persistent workspace and state storage.

From the documentation

OpenHands runs as a web application on port 3000 and stores workspace data under /workspace and application state under /root/.openhands-state. The template exposes the UI through Sealos HTTPS ingress and lets you provide optional LLM settings during deployment.

How to deploy OpenHands

  1. Choose Deploy now to start OpenHands in your Sealos workspace.
  2. Review llm_api_key, llm_model in the deployment form.
  3. Launch the template, then inspect the application status and resource cards in Canvas.

Resources to plan for

Start with the resources defined by the OpenHands template. Review CPU, memory, persistent storage, and network allocations for every service in Canvas. Capacity needs depend on your data and workload; monitor usage as they grow.

Template configuration and setup

Access after deployment

Use the application URL or connection details shown in Canvas. Follow the deployment guide for first-time account setup or client configuration, and keep generated credentials available for that step.

Hosting and billing

Sealos monthly plans include compute, memory, storage, and traffic. Size your plan for all deployed services. Software licenses and external AI or API services may have separate terms and charges. Confirm the applicable plan and optional charges in Cost Center.

Compare Sealos resource plans
Read full documentationCollapse documentation

For current cloud charges, refer to Sealos plan pricing. Upstream documentation may reference earlier billing models.

Deploy and Host OpenHands on Sealos

OpenHands is an AI software development agent web application. This template deploys the OpenHands web UI on Sealos Cloud with persistent workspace and state storage.

OpenHands Screenshot

About Hosting OpenHands

OpenHands runs as a web application on port 3000 and stores workspace data under /workspace and application state under /root/.openhands-state. The template exposes the UI through Sealos HTTPS ingress and lets you provide optional LLM settings during deployment.

OpenHands' full Docker sandbox mode normally requires access to a Docker daemon. This Sealos template provides a reachable web deployment path with persistent workspace storage and validates the UI/runtime startup path. Agent execution that requires launching nested sandbox containers depends on platform-level Docker/runtime support.

Common Use Cases

  • AI coding workspace: Open a browser-based OpenHands UI for project automation.
  • LLM agent experiments: Connect an LLM API key and test agent workflows.
  • Persistent task state: Keep workspace files and OpenHands state across restarts.
  • Cloud development assistant: Run an assistant-style web app next to other Sealos services.

Dependencies for OpenHands Hosting

The Sealos template includes the OpenHands web container, persistent workspace storage, persistent state storage, public HTTPS ingress, and optional LLM configuration inputs.

Deployment Dependencies
Implementation Details

Architecture Components:

  • OpenHands StatefulSet: Runs ghcr.io/openhands/openhands:1.8.0 on port 3000.
  • Workspace volume: Persists /workspace.
  • State volume: Persists /root/.openhands-state.
  • Ingress and App: Publish the OpenHands web UI through HTTPS.

Configuration:

  • llm_api_key is optional and maps to LLM_API_KEY.
  • llm_model is optional and maps to LLM_MODEL.
  • SANDBOX_RUNTIME_CONTAINER_IMAGE points to the matching OpenHands runtime image on GHCR.
  • Full nested-container execution depends on Docker/runtime availability in the Sealos environment.

License Information:

OpenHands is licensed under MIT. This Sealos template is provided under the repository license.

Why Deploy OpenHands on Sealos?

Sealos is an AI-assisted Cloud Operating System built on Kubernetes that unifies the entire application lifecycle, from development in cloud IDEs to production deployment and management. By deploying OpenHands on Sealos, you get:

  • One-Click Web UI: Start the OpenHands web app quickly.
  • Persistent Workspace: Keep workspace and state data across restarts.
  • Optional LLM Setup: Provide model and API key values during deployment.
  • Instant Public Access: Access the UI through an HTTPS URL.
  • Integrated Operations: Inspect logs, restart the app, and adjust resources from the Canvas.

Deployment Guide

  1. Open the OpenHands template and click Deploy Now.
  2. Optionally provide llm_api_key and llm_model.
  3. Wait for deployment to complete. After deployment, you will be redirected to the Canvas.
  4. Open the OpenHands URL.
  5. Configure the LLM provider in the UI when prompted, then open the main workspace page.

Configuration

After deployment, configure OpenHands through:

  • OpenHands UI: Set or confirm the LLM provider and model.
  • AI Dialog: Describe resource or environment changes and let Sealos apply them.
  • Resource Cards: Adjust CPU, memory, storage, and environment variables.

Runtime Notes

The template validates the OpenHands web application path and persistent storage path. Workflows that require starting sandbox runtime containers need Docker-compatible runtime access from the hosting environment. For code editing, UI setup, and state persistence, the deployment works as a normal web app.

Troubleshooting

Agent execution cannot start a sandbox
  • Cause: The hosting environment does not expose a Docker daemon or compatible nested runtime to the OpenHands container.
  • Solution: Use OpenHands UI features that do not require nested runtime containers, or attach a supported runtime service according to OpenHands runtime documentation.
LLM calls fail
  • Cause: Missing or invalid provider credentials.
  • Solution: Set llm_api_key and llm_model during deployment or update them from the StatefulSet environment variables.

Additional Resources

License

This Sealos template is provided under the repository license. OpenHands itself is licensed under MIT.

From launch to everyday operations

Why deploy
on Sealos

A shorter path from an app you want to an app you can run. Sealos brings deployment and ongoing operations into one place.

  1. One-click deployment

    Start with a ready-made template. Review its configuration and launch from the Sealos console.

  2. Managed Kubernetes

    Run on managed infrastructure with built-in workload scheduling and recovery.

  3. Automatic HTTPS

    Give your application a public HTTPS endpoint with certificates managed for you.

  4. Persistent storage

    Keep application data on persistent volumes across container restarts.

  5. Room to grow

    Adjust CPU, memory, and replicas from the console as your workload changes.

One template. Connected resources.

You Get the Whole Stack

Sealos provisions the resources defined by your template and brings them together in your workspace.

  • App Service

    Container workloads with configurable CPU, memory, and replicas.

  • Public HTTPS URL

    An address for your app, with managed TLS certificates.

  • Database

    A database provisioned alongside your app when the template calls for one.

  • Persistent Volume

    Storage for the files and data your application needs to keep.

  • Environment Variables

    Application settings and secrets configured in one place.

  • Logs & Metrics

    Inspect container logs and resource usage from the console.

Resources and their configuration vary by template. Review the deployment form for this app’s exact setup.

Explore more production-ready templates.

More