We're excited to announce that our Pull Request was officially merged into OpenHands' main branch today, making Daytona Runtime an official runtime option for OpenHands.
Daytona is committed to empowering developers to easily and confidently build, deploy, and scale AI-driven applications. This new runtime marks a significant milestone in our mission to provide a secure, elastic, and user-friendly infrastructure tailored for modern AI workflows.
AI-generated code is revolutionizing development, but executing it safely remains a challenge. Traditional runtimes lack the isolation, security, and scalability for AI's unpredictable workloads. Without proper safeguards, AI code risks resource abuse, security breaches, or system instability.
Enter Daytona Runtime for OpenHands—a purpose-built solution to run AI-generated code securely while maintaining developer-friendly workflows.
What is Daytona Runtime for OpenHands?
This new integration replaces OpenHands' default Docker runtime with Daytona's elastic infrastructure. Instead of local containers, your AI code runs in Daytona's isolated, cloud-hosted sandboxes. Key benefits include:
Zero-Trust Security: Each execution environment is sandboxed, preventing unauthorized access.
Dynamic Scaling: Automatically allocates CPU/memory based on workload demands.
Preview URLs: No more localhost:port—Daytona generates secure, shareable URLs for running apps.
Key Features of Daytona Runtime for OpenHands
1. Secure Execution by Default
Every OpenHands sandbox runs in a Daytona workspace with:
Resource Limits: Prevent CPU/memory overuse.
Network Controls: Restrict outbound traffic.
Ephemeral Environments: Fresh instances for each session, eliminating residual state risks.
2. Seamless Preview URLs
Daytona automatically replaces localhost ports with dedicated URLs (e.g., https://5000-sandbox123.node456.daytona.io). No more manual port forwarding or complex proxies!
3. Global Elastic Infrastructure
Deploy sandboxes in multiple regions (us or eu) to optimize latency and comply with data residency requirements.
Getting Started in 2 Minutes
1. Set Your API Key as an Environment Variable:
Run the following command in your terminal, replacing <your-api-key> with the actual key you copied:
1export DAYTONA_API_KEY="<your-api-key>"
2. Run OpenHands Locally Using Docker:
To start the latest version of OpenHands on your machine, execute the following command in your terminal:
1bash -i <(curl -sL https://get.daytona.io/openhands)
Daytona automatically provisions sandboxes in the cloud.
Why Developers Love Daytona
No Infrastructure Overhead: Daytona handles provisioning, scaling, and cleanup.
Unified Workflow: Use the same OpenHands interface—no new tools to learn.
Cost-Effective: Pay only for active compute time, with a $30 credit for new users.
Use Case: Safe AI Code Evaluation
Imagine an AI coding assistant generating a Python script. With Daytona Runtime:
The code runs in a sandbox with restricted permissions.
Resource limits prevent infinite loops from crashing your machine.
Results are streamed back, and the workspace self-destructs post-execution.
What's Next?
Proxy Integration: Directly map local ports to Daytona URLs (coming Q2).
Enhanced Observability: Real-time metrics for CPU, memory, and network usage.
The runtime is available now as part of the latest OpenHands release. You can check out the merged PR #6863 here. We look forward to seeing what you build with these new secure sandbox capabilities!
By adopting Daytona Runtime, you're not just executing code—you're future-proofing your AI workflows. Focus on innovation, and let Daytona handle the rest.
