OpenHands CLI Guide
The former OpenHands terminal client, retained here for existing installations and migration research.
Last verified: · How we verifyThe official repository says this CLI is no longer actively maintained and recommends Agent Canvas.
Suitable workflows
Maintaining an existing OpenHands CLI setup and understanding its configuration.
Limitations and billing
The official repository says this CLI is no longer actively maintained and recommends Agent Canvas.
Capabilities we verified
This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.
Pricing & usage
See official pricing
Legacy client; configured provider and infrastructure costs. The cost of metered usage or an external agent can be separate from the subscription.
Check official pricing ↗Models & access
Configure the LLM provider supported by your installed version.
Official model information ↗Install and start the CLI
Legacy installation requires Python 3.12+ and uv 0.11.6+; check migration guidance before installing.
Installation command · Python / uv
uv tool install openhands --python 3.12Open your project folder in a terminal, then run:
openhandsAccount and authentication
The first-run wizard configures the LLM provider used by the existing client.
Project configuration and tools
Settings live under ~/.openhands/. Environment overrides require --override-with-envs in the documented version.
First task to try
Inspect an existing setup and its provider settings before deciding whether to migrate.
Script usage
This example asks for a project summary. Tool permissions still apply; a prompt is not a sandbox.
openhands --headless -t "Summarize the project structure without modifying files."Related CLI tools
All AI CLI tools →
Project evaluation checklist
- Open a small, familiar project and confirm that your essential language tooling works.
- Give the agent one bounded change with an observable acceptance criterion.
- Review the diff, run the project’s checks and compare the result with your current workflow.
- Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.