browser-harness
Direct browser control via CDP — automate, scrape, test, or interact with web pages by driving the user's already-running Chrome (or a Browser Use cloud browser). Use when the user wants to click, screenshot, fill forms, extract data, or navigate real web pages. Default to screenshots + coordinate clicks, not selector hunting. Requires the one-time `browser-harness` CLI install (see references/install.md).
pinned to #8a715b8updated last month
Ask your AI client: “install skills/browser-harness”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install skills/browser-harnessmetahub onboarded this repo on the author's behalf.
If you own github.com/browser-use/browser-harness on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
15,160
Last commit
last month
Latest release
published
- #ai-agent
- #browser-agent
- #browser-automation
- #browser-use
- #browser-use-box
- #browser-use-cloud
- #cdp
- #cloud-browser
- #llm
- #persistent-browser
- #playwright
- #telegram-agent
- #vps-agent
- #web-automation
About this skill
Pulled from SKILL.md at publish time.
Direct browser control via CDP. You drive the user's real browser with Python helpers run through the `browser-harness` command.
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.8a715b8· last month
Documentation
41Description quality
60 words · 409 chars — "Direct browser control via CDP — automate, scrape, test, or interact with web pa…"
README is present and substantial
3,865 chars · 5 sections · 2 code blocks
Tags / topics declared
14 total — ai-agent, browser-agent, browser-automation, browser-use, browser-use-box, browser-use-cloud (+8)
README has usage / example sectionswarn
README has no Usage / Example / Quick start / Installation heading at any level
Add a `# Usage`, `## Quick start`, or similar section so end users can copy/paste a working invocation. Code blocks alone work too if there are several.
Homepage / docs URL declared
https://browser-harness.com
Release history
1- releasecurrent8a715b8warnlast month
Contents
Browser Harness ♞
Connect an LLM directly to your real browser with a thin, editable CDP harness. For browser tasks where you need complete freedom.
One websocket to Chrome, nothing between. The agent writes what's missing during execution. The harness improves itself every run.
Try browser-harness in Browser Use Cloud or paste the setup prompt into your coding agent.
● agent: wants to upload a file
│
● agent-workspace/agent_helpers.py → helper missing
│
● agent writes it agent_helpers.py
│ + custom helper
✓ file uploaded
You will never use the browser again.
Setup prompt
Paste into Claude Code or Codex:
Set up https://github.com/browser-use/browser-harness for me.
Read `install.md` and follow the steps to install browser-harness and connect it to my browser.
The agent will open chrome://inspect/#remote-debugging. Tick the checkbox so the agent can connect to your browser:
Remote debugging setup
Click Allow when the per-attach popup appears (Chrome 144+):
Allow remote debugging popup
See agent-workspace/domain-skills/ for example tasks.
Free Browser Use Cloud browsers
Stealth, sub-agents, or headless deployment.
Browser Use Cloud free tier: 3 concurrent browsers, proxies, captcha solving, and more. No card required.
- Grab a key at cloud.browser-use.com/new-api-key
- Or let the agent sign up itself via docs.browser-use.com/llms.txt (setup flow + challenge context included).
Architecture (~1k lines across 4 core files)
install.md— first-time install and browser bootstrapSKILL.md— day-to-day usagesrc/browser_harness/— protected core packageagent-workspace/agent_helpers.py— helper code the agent editsagent-workspace/domain-skills/— reusable site-specific skills the agent edits
Contributing
PRs and improvements welcome. The best way to help: contribute a new domain skill under agent-workspace/domain-skills/ for a site or task you use often (LinkedIn outreach, ordering on Amazon, filing expenses, etc.). Each skill teaches the agent the selectors, flows, and edge cases it would otherwise have to rediscover.
- Skills are written by the harness, not by you. Just run your task with the agent — when it figures something non-obvious out, it files the skill itself (see SKILL.md). Please don't hand-author skill files; agent-generated ones reflect what actually works in the browser.
- Open a PR with the generated
agent-workspace/domain-skills/<site>/folder — small and focused is great. - Bug fixes, docs tweaks, and helper improvements are equally welcome.
- Browse existing skills (
github/,linkedin/,amazon/, ...) to see the shape.
If you're not sure where to start, open an issue and we'll point you somewhere useful.
Domain skills
Set BH_DOMAIN_SKILLS=1 to enable agent-workspace/domain-skills/ — community-contributed per-site playbooks goto_url surfaces by domain. Contribute via PR.
The Bitter Lesson of Agent Harnesses · Web Agents That Actually Learn
Reviews
No reviews yet. Be the first.
Related
Browser Use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Guizang Ppt Skill
AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.
Verification Before Completion
Evidence before assertions, always
mh install skills/browser-harness