BrowserUse_and_ComputerUse_.../browser-use/SKILL.md
2026-03-26 22:08:01 +03:00

2.7 KiB

name version description triggers allowed-tools
browser-use 1.0.0 Use browser-use with a Chromium CDP endpoint to perform web tasks from Hermes.
browser-use
open website and extract
automate browser task
run browser task
terminal
file
memory

Browser Use (Chromium)

This skill runs browser tasks via browser-use and connects to Chromium through CDP.

Prerequisites

  • hermes-agent container is running
  • chromium service is running in docker-compose
  • OPENAI_API_KEY is present in container env (via docker-compose env_file)
  • If running outside container, set OPENAI_API_KEY in your shell or .env

Troubleshooting Environment Setup

If you get {"success": false, "error": "OPENAI_API_KEY is not set"}:

docker compose exec -T hermes-agent python - <<'PY'
import os
print('OPENAI_API_KEY', '<set>' if os.getenv('OPENAI_API_KEY') else '<missing>')
print('OPENAI_BASE_URL', '<set>' if os.getenv('OPENAI_BASE_URL') else '<missing>')
PY

If OPENAI_API_KEY is missing, ensure key exists in one of env files used by compose:

  • workspace/.env
  • hermes_data/.env

Then recreate container:

docker compose up -d hermes-agent
# Optional overrides when running outside Docker
export OPENAI_API_KEY="your-api-key-here"
export BROWSER_USE_CDP_URL="ws://chromium:3000/chromium?token=hermes-local"

Common failure: {"success": false, "error": "OPENAI_API_KEY is not set"}

  • Cause: key is absent in container env
  • Fix: add key to workspace/.env or hermes_data/.env, then docker compose up -d hermes-agent

Common failure: 401 key_model_access_denied

  • Cause: API key cannot access configured model (for example gpt-4o-mini)
  • Fix: set allowed model via BROWSER_USE_MODEL (or OPENAI_MODEL) to a model your provider key can use

Common failure: Connection refused to chromium

  • Cause: Browser not running or CDP endpoint wrong
  • Fix: Check docker-compose ps and verify chromium service is up

Quick start

python-browser-use /root/.hermes/skills/autonomous-ai-agents/browser-use/scripts/run_browser_use.py \
  --task "Open example.com and return page title" \
  --max-steps 8

How to use in Hermes

When user asks for website automation:

python-browser-use /root/.hermes/skills/autonomous-ai-agents/browser-use/scripts/run_browser_use.py \
  --task "<user task in plain language>" \
  --max-steps 20

If user gives a start URL, pass --start-url.

Notes

  • Default CDP URL: ws://chromium:3000/chromium?token=hermes-local
  • Override by setting BROWSER_USE_CDP_URL
  • Runtime Python: BROWSER_USE_PYTHON (defaults to python-browser-use)
  • The script outputs JSON for easy parsing