openhands

Delegate coding tasks to the OpenHands CLI in headless JSON mode.

Updated Jun 15, 2026
One-click install
npx skills add https://github.com/faramirezs/talking_printer --skill openhands-faramirezs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openhands
Source: https://github.com/faramirezs/talking_printer/tree/main/hermes-agent/optional-skills/autonomous-ai-agents/openhands
Command: npx skills add https://github.com/faramirezs/talking_printer --skill openhands-faramirezs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The OpenHands CLI enables automated, provider-agnostic delegation of coding tasks, eliminating manual handoffs and UI constraints.

Core Features & Use Cases

  • Headless batch or single-shot coding task delegation via the terminal.
  • Model-agnostic support for LiteLLM providers, with environment-based configuration.
  • Clear, deterministic JSONL output for automation and integration.

Quick Start

Run OpenHands in headless JSON mode with environment variables configured to your provider and task the agent to delegate the coding work.

Frequently Asked Questions about openhands

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I delegate coding tasks to the OpenHands CLI in headless mode?

To delegate coding tasks to the OpenHands CLI, run it in headless JSON mode via the terminal tool. Configure your provider using the LLM_MODEL, LLM_API_KEY, and LLM_BASE_URL environment variables to automate single or batch workflows.

Can I use OpenHands with any LLM provider through LiteLLM?

Yes, OpenHands supports model-agnostic coding delegation through LiteLLM providers. You configure your chosen provider by setting the LLM_MODEL, LLM_API_KEY, and LLM_BASE_URL environment variables before executing the terminal task.

How do I ensure deterministic JSON output when automating coding workflows?

Deterministic JSON output is ensured by running the OpenHands CLI with specific flags: --headless --json --override-with-envs --exit-without-confirmation. This configuration enforces environment variable overrides and prevents interactive prompts.

What is the best way to automate batch coding tasks without manual UI interaction?

The best way to automate batch coding tasks without UI interaction is delegating them to the OpenHands CLI. It operates headless in JSON mode, eliminating manual handoffs and UI constraints while processing multiple tasks sequentially.

Does OpenHands CLI require interactive confirmation for automated task execution?

No, the OpenHands CLI does not require interactive confirmation for automated task execution. By applying the --exit-without-confirmation flag alongside headless and JSON mode flags, the terminal tool exits automatically upon task completion.

Why does OpenHands use environment variables for LLM configuration?

OpenHands uses environment variables like LLM_MODEL, LLM_API_KEY, and LLM_BASE_URL for LLM configuration to enable provider-agnostic automation. This approach allows seamless integration across different LiteLLM providers without modifying internal task execution logic.