Agentic power from the command line.

Run, inspect, and automate OpenHands agents directly from the terminal or headlessly in your pipelines with full visibility and control.

ASCII art depicting a large black hole with light and particles swirling around it.

A first-class terminal and CLI interface for autonomous agents.

The OpenHands Terminal / CLI gives developers direct, low-latency control over cloud-based coding agents. Use it interactively from your terminal or run it headlessly from CI, cron jobs, or internal systems.

Same agent. Same runtime. Two modes of control.

Real autonomy needs observability and repeatability.

IDE assistants are fine for small edits. Real agentic work requires visibility into what ran, where it ran, and what changed. OpenHands’ Terminal / CLI lets you see exactly what the agent did, inspect outputs, and re-run tasks deterministically.

No babysitting. No abstraction leaks.

Key capabilities

Intuitive and powerful Terminal UX
Save and resume conversations
Use with your favorite IDE via ACP
Headless mode for CI/CD and background tasks
Confirmation mode for safe, local execution
Seamlessly integrates with OpenHands Cloud

How teams use it

Fix bugs before standup
Run repo-wide maintenance and refactors
Trigger agents from CI pipelines
Upgrade dependencies nightly
Remediate vulnerabilities before merge
Automate linting and test cleanup

The only open, secure, and scalable agent platform built for real engineering work

Feature	OpenHands	Devin	Claude Code	Factory
Open-source
Model-agnostic
Sandbox runtime
Self-hosted
Coding Agent SDK

Control your agents like real infrastructure.

Run OpenHands from the terminal or automate it end to end with the CLI.