# OpenHands Delegation

Hand coding work to the model-agnostic OpenHands CLI.

- Repository: https://github.com/NousResearch/hermes-agent (259479 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add NousResearch/hermes-agent --skill openhands -g -a claude-code -y`
Codex: `npx skills add NousResearch/hermes-agent --skill openhands -g -a codex -y`
Cursor: `npx skills add NousResearch/hermes-agent --skill openhands -g -a cursor -y`
Gemini CLI: `npx skills add NousResearch/hermes-agent --skill openhands -g -a gemini-cli -y`

## Description

Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# OpenHands CLI

Delegate coding tasks to the [OpenHands CLI](https://github.com/All-Hands-AI/OpenHands) via the `terminal` tool. OpenHands is model-agnostic: any LiteLLM-supported provider (OpenAI, Anthropic, OpenRouter, DeepSeek, Ollama, vLLM, etc.).

This skill is the headless-mode wrapper for batch / one-shot delegation. The interactive textual UI is not used from Hermes.

## When to Use

- User wants a coding task delegated to OpenHands specifically.
- User wants a coding agent that can run on a non-Anthropic / non-OpenAI provider (DeepSeek, Qwen, Ollama, vLLM, Nous, etc.), sibling skills `claude-code` and `codex` are tied to one vendor.
- Multi-step file edits + shell commands inside a workspace.

For Claude-native, prefer `claude-code`. For OpenAI-native, prefer `codex`. For Hermes-native subagents, use `delegate_task`.

## Prerequisites

1. Install upstream (requires Python 3.12+ and `uv`):

   ```
   terminal(command="uv tool install openhands --python 3.12")
   ```

   Verify: `openhands --version` (currently `OpenHands CLI 1.16.0` / `SDK v1.21.0` at time of writing).

2. Pick a model and set env vars for `--override-with-envs`:

   ```
   export LLM_MODEL=openrouter/openai/gpt-4o-mini       # or any LiteLLM slug
   export LLM_API_KEY=$OPENROUTER_API_KEY
   export LLM_BASE_URL=https://openrouter.ai/api/v1     # omit for native OpenAI
   ```

   `LLM_MODEL` uses LiteLLM's full slug. When the provider is OpenRouter the slug is doubly-prefixed: `openrouter/<vendor>/<model>` (e.g. `openrouter/anthropic/claude-sonnet-4.5`). For native Anthropic: `anthropic/claude-sonnet-4-5`. For native OpenAI: `openai/gpt-4o-mini`.

3. Suppress the startup banner so JSON output isn't preceded by ASCII art:

   ```
   export OPENHANDS_SUPPRESS_BANNER=1
   ```

## How to Run

Always invoke through the `terminal` tool. Always pass `--headless --json --override-with-envs --exit-without-confirmation` for automation.

### One-shot task

The rest: https://github.com/NousResearch/hermes-agent/blob/HEAD/optional-skills/autonomous-ai-agents/openhands/SKILL.md