# Show HN： 浏览器框架--赋予大型语言模型（LLM）自由完成任何浏览器任务的能力

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：gregpr07
- 发布时间：2026-04-25 17:33
- AIHOT 分数：58
- AIHOT 链接：https://aihot.virxact.com/items/cmoe5hlu7012gsl1nqwr6205x
- 原文链接：https://github.com/browser-use/browser-harness

## AI 摘要

开源项目“Browser Harness”发布，旨在赋予大型语言模型（LLM）在浏览器中自主完成任意任务的能力。该工具通过提供一个可编程的浏览器控制框架，使LLM能够像人类一样操作网页，执行点击、输入、导航等复杂交互。此举有望突破当前AI代理在自动化网络操作方面的限制，扩展LLM的实际应用场景。该项目已在GitHub开源，并在Hacker News社区获得100点热度关注。

## 正文

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

● 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.

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:

chrome://inspect/#remote-debugging

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 bootstrap

install.md

SKILL.md — day-to-day usage

SKILL.md

src/browser_harness/ — protected core package

src/browser_harness/

agent-workspace/agent_helpers.py — helper code the agent edits

agent-workspace/agent_helpers.py

agent-workspace/domain-skills/ — reusable site-specific skills the agent edits

agent-workspace/domain-skills/

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// folder — small and focused is great.

agent-workspace/domain-skills//

Bug fixes, docs tweaks, and helper improvements are equally welcome.

Browse existing skills (github/, linkedin/, amazon/, ...) to see the shape.

github/

linkedin/

amazon/

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.

BH_DOMAIN_SKILLS=1

goto_url

The Bitter Lesson of Agent Harnesses · Web Agents That Actually Learn