项目文件夹
Laith Weinberger
ff049266b1
- Classify the connection up front (browser.py): read DevToolsActivePort + Local State and return ok / cdp-disabled / permission-blocked / browser-closed in ~0.01s, without opening a tab. Each blocked state's error carries its own fix, so the agent relays one line and retries instead of hanging or exploring. - Defer the marker tab until after the websocket connects, so a failed connection doesn't leave a stray tab. - Reuse stays in the right profile: on daemon reuse, verify the controlled tab still belongs to the selected context and re-anchor if it drifted or closed (verify_profile). On a stale session, re-attach the same tab instead of grabbing an arbitrary page. - admin.py routing: a 403 is permission-blocked on its own (focus the profile, don't tell the user to re-tick the checkbox); browser-closed opens/focuses the selected profile. - Drop the BH_CLOUD_ONLY env var and its guard.
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.
● 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:
Click Allow when the per-attach popup appears (Chrome 144+):
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