Local Runtime

​

Prerequisites

Before using the Local Runtime, ensure that:

1. You can run OpenHands using the Development workflow.
2. For Linux and Mac, tmux is available on your system.
3. For Windows, PowerShell is available on your system.
   • Only CLI mode and headless mode are supported in Windows with Local Runtime.

​

Configuration

To use the Local Runtime, besides required configurations like the LLM provider, model and API key, you’ll need to set the following options via environment variables or the config.toml file when starting OpenHands:

Via environment variables (please use PowerShell syntax for Windows PowerShell):

# Required
export RUNTIME=local

# Optional but recommended
# The agent works in /workspace by default, so mount your project directory there
export SANDBOX_VOLUMES=/path/to/your/workspace:/workspace:rw
# For read-only data, use a different mount path
# export SANDBOX_VOLUMES=/path/to/your/workspace:/workspace:rw,/path/to/large/dataset:/data:ro

Via config.toml:

[core]
runtime = "local"

[sandbox]
# The agent works in /workspace by default, so mount your project directory there
volumes = "/path/to/your/workspace:/workspace:rw"
# For read-only data, use a different mount path
# volumes = "/path/to/your/workspace:/workspace:rw,/path/to/large/dataset:/data:ro"

If SANDBOX_VOLUMES is not set, the runtime will create a temporary directory for the agent to work in.

​

Example Usage

Here’s an example of how to start OpenHands with the Local Runtime in Headless Mode:

export RUNTIME=local
export SANDBOX_VOLUMES=/my_folder/myproject:/workspace:rw

poetry run python -m openhands.core.main -t "write a bash script that prints hi"

​

Use Cases

The Local Runtime is particularly useful for:

• CI/CD pipelines where Docker is not available.
• Testing and development of OpenHands itself.
• Environments where container usage is restricted (e.g. native Windows).