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/agenthelpers.py → helper missing │ ● agent writes it agenthelpers.py │ + custom helper ✓ file uploaded
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
Videos
He just crawled through hell to fix the browser…
Fireship · 1263K views
This Browser Agent Can Do Anything (or They Buy You A Mac Mini)
Eric Michaud · 29K views
Spotlighting Browser Harness: A Self-healing Browser Agent (Must Watch!)
John Fáwọlé · 1K views
What people are saying
“Hey HN, We got tired of browser frameworks restricting the LLM, so we removed the framework and gave the LLM maximum freedom to do whatever it's trained on. We gave the harness the ability to self correct and add new too…”
HN↑ 134gregpr07↗
“Creator of browser-use library here. At Browser Use we spend a lot of time thinking about the bitter lesson of agentic frameworks. A few days we did an experiment that combines replacing Playwright with CDP and giving th…”
HN↑ 3gregpr07↗
“Browser Use Box: run Browser Harness on your own always-on box — [](https://www.tiktok.com/@browser_use/video/7639824093721758989) Browser Use Box is now available as a self-hosted path for people who want Browser Harnes…”
GH↑ 1ShawnPana↗
“How to avoid 'allow' prompts? — This skill is really useful but when I am working wiht 10 different agents getting these permissions prompts is very very annoying. I have already enabled remote debugging, how can I allow…”
GH↑ 1lucascastellanibr↗
“Dgx Spark ( headless ) — 1. On headless environments (like DGX Spark), Chrome must be pre-launched with --headless=new 2. Snap Chromium on Ub…”
GH↑ 1adrianpuiu↗
You might also like
AI
career ops
Companies use AI to filter candidates. I just gave candidates AI to choose companies. Career-Ops (career-ops.org, also known as careerops) turns any AI coding CLI into a full job search command center. Instead of manually tracking applications in a spreadsheet, you get an AI-powered pipeline that: Career-ops is agentic: Claude Code navigates career pages with Playwright, evaluates fit by reasoning about your CV vs the job description (not keyword matching), and adapts your resume per listing.
AI
CLI Anything
CLI-Anything: Bridging the Gap Between AI Agents and the World's Software 🌐 CLI-Hub: pip install cli-anything-hub then cli-hub install — browse, install, and manage all community-built CLIs. Want to add your own? Open a PR — the hub updates instantly. 🎬 See Demos: Watch AI agents use generated CLIs plus preview, live preview, and trajectory loops to produce real artifacts — CAD builds, 3D scenes, diagrams, gameplay, subtitles, and more.
AI
odysseus
A self-hosted AI workspace -- meant to be the self-hosted version of the UI experience you get from ChatGPT and Claude. But with more jank and fun. Running on your own hardware, with your own data -- local-first, privacy-first, and no trojan. A full, hover-to-play tour lives on the landing page (docs/index.html). Defaults work out of the box: clone, run, then configure models/search/email inside Settings. Only edit .env for deployment-level overrides like APPBIND, APPPORT, AUTHENABLED, DATABASEURL, or a pre-seeded admin password.
AI
ai engineering from scratch
Most AI material teaches in scattered pieces. A paper here, a fine-tuning post there, a flashy agent demo somewhere else. The pieces rarely line up. You ship a chatbot but can't explain its loss curve. You hook a function to an agent but can't say what attention does inside the model that's calling it. This curriculum is the spine. 20 phases, 503 lessons, four languages: Python, TypeScript, Rust, Julia. Linear algebra at one end, autonomous swarms at the other. Every algorithm gets built from raw math first. Backprop. Tokenizer. Attention. Agent loop. By the time PyTorch shows up, you already know what it's doing under the hood. Each lesson runs the same loop: read the problem, derive the math, write the code, run the test, keep the artifact. No five-minute videos, no copy-paste deploys,