How-To Guide
Run Hermes in Daytona Cloud Workspaces
Configure Hermes Agent to execute commands in Daytona's managed cloud development environments — persistent workspaces with team collaboration.
Quick answer
The Daytona terminal backend runs Hermes commands in managed cloud development workspaces — persistent environments that feel local but live in the cloud. It fits teams that want consistent, reproducible environments rather than ephemeral containers. Configure it with your Daytona workspace credentials.
Daytona provides managed cloud development environments — persistent workspaces that feel like local development but run in the cloud. Great for teams, consistent environments, and when you need more than ephemeral containers.
Managed cloud · API costs included · Skill library · Cancel anytime
Before you start:
- ☑Hermes Agent installed
- ☑Daytona account with API key
- ☑Daytona SDK installed (pip install daytona)
Steps
- 1
Install Daytona SDK
pip install daytona
- 2
Get your API key
Sign up at daytona.io and get your API key from the dashboard
- 3
Add the API key to .env
Add DAYTONA_API_KEY=your_key_here to ~/.hermes/.env
- 4
Configure the backend
In config.yaml, set terminal: backend: daytona
- 5
Choose a workspace image
Set terminal: daytona_image: nikolaik/python-nodejs:python3.11-nodejs20
- 6
Start using Hermes
Commands now execute in Daytona cloud workspaces
Pro Tips
- 💡Daytona workspaces are persistent by default — your files and environment survive restarts
- 💡Maximum disk size is 10GB per sandbox on Daytona
- 💡Great for team collaboration — multiple agents can share the same workspace
- 💡Daytona supports Git integration for automatic repository cloning
Troubleshooting
❌ Invalid API key error
✅ Verify your DAYTONA_API_KEY in ~/.hermes/.env matches your dashboard. Regenerate the key if needed.
❌ Workspace disk full
✅ Daytona limits sandboxes to 10GB. Clean up unused files or create a new workspace.
❌ Slow workspace provisioning
✅ First workspace creation pulls the image. Subsequent workspaces using the same image are faster.
FAQ
How is Daytona different from the Docker backend?
Docker gives ephemeral, isolated containers. Daytona gives persistent managed cloud workspaces that feel like local dev — better when you need continuity and consistency across a team.
Who is the Daytona backend for?
Teams and anyone who wants reproducible, persistent environments rather than throwaway containers, while keeping execution off their local machine.
Does the workspace persist between sessions?
Yes — that's the point. Unlike ephemeral containers, Daytona workspaces retain state so the agent returns to a consistent environment.