Playwright on KnightLi Blog

browser-harness, Playwright, and Puppeteer: which browser automation tool should you choose?

Sun, 24 May 2026 17:51:28 +0800

In browser automation and automated testing, Playwright and Puppeteer are two of the most commonly compared tools. Both can control browsers, click pages, extract content, generate screenshots or PDFs, and both are closely related to Chrome DevTools Protocol.

Once browser-use/browser-harness is added to the picture, the question is no longer simply “which testing framework is stronger.” It becomes a comparison between two kinds of tools:

Playwright / Puppeteer: tools for engineers to write deterministic scripts.
browser-harness: a tool for AI agents to operate real browsers.

The first group fits testing, scraping, and engineered automation. The second is closer to a browser control layer for agents such as Claude Code, Codex CLI, and Gemini.

The relationship between Playwright and Puppeteer

Puppeteer was originally launched by the Google Chrome team and naturally focuses on Chromium and Chrome automation. Its API is concise, the ecosystem is mature, and it is especially convenient for screenshots, PDF generation, page scraping, and lightweight automation around Chrome.

Playwright is maintained by Microsoft, and its team has deep historical links to early Puppeteer work. It absorbed many lessons from Puppeteer and added stronger cross-browser support, auto-waiting, context isolation, test reports, and debugging tools.

In short:

If you only need lightweight Chrome-based tasks, Puppeteer is still very pleasant to use.
If you are doing cross-browser E2E tests, complex SPA automation, or team-level test engineering, Playwright is usually the better fit.

Core differences

Dimension	Puppeteer	Playwright
Maintainer	Google	Microsoft
Browser support	Mainly Chrome / Chromium	Chromium, Firefox, WebKit
Language support	Mainly JavaScript / TypeScript	JavaScript / TypeScript, Python, Java, .NET
Auto-waiting	More explicit waiting	Strong Locator and auto-waiting
Context isolation	Supported, but less central	Excellent BrowserContext workflow
Tooling	Simple, mature, foundational	Codegen, Trace Viewer, reports
Typical use	Chrome automation, screenshots, PDF, lightweight scraping	Cross-browser E2E tests, complex frontend automation

Browser support

Puppeteer is strongest with Chrome. It integrates tightly with Chromium. If your goal is to control Chrome, generate PDFs, take screenshots, or run simple scraping tasks, Puppeteer has a low mental overhead.

Playwright is stronger for cross-browser work. It natively supports Chromium, Firefox, and WebKit. WebKit is especially important because many Safari-related issues cannot be detected through Chrome alone. For applications that need coverage across desktop, mobile, and multiple browser engines, Playwright is the better main tool.

This is the first decision boundary: if you only care about Chrome, Puppeteer is fine. If you are serious about cross-browser testing, choose Playwright first.

Auto-waiting and stability

The most annoying part of browser automation is often not “how to click,” but whether the page is ready. An element may not be attached to the DOM, may be covered, may still be animating, or may still be disabled.

In Puppeteer, you often write:

1
2

await page.waitForSelector('#submit-btn');
await page.click('#submit-btn');

This works, but engineers must think through the waiting logic themselves. The more complex the page, the more likely the script will accumulate waitForSelector, waitForTimeout, and retry logic.

Playwright’s Locator and auto-waiting mechanism is more complete:

`1`	`await page.locator('#submit-btn').click();`

Before clicking, Playwright checks whether the element is visible, actionable, stable, and not covered, then retries within a reasonable time. This matters a lot for modern React, Vue, and Next.js applications with heavy asynchronous rendering, and it reduces flaky tests.

Multi-account workflows and context isolation

If you need to simulate multiple users, or let many tasks share one browser process while isolating Cookie, LocalStorage, and Session, BrowserContext matters.

Puppeteer also supports context isolation, but Playwright makes it a core capability. You can quickly create multiple independent contexts inside one browser instance. Each context behaves like a clean browser environment without repeatedly starting full browser processes.

This is useful for:

Multi-account concurrent tests.
Multi-role workflow tests.
Ecommerce, messaging, and collaborative document scenarios.
Scraping tasks that need isolated Cookie and login state.

Tooling differences

Playwright is the more engineering-oriented option. It includes many tools used in test development:

codegen: operate on a webpage and generate scripts automatically.
Trace Viewer: replay screenshots, DOM snapshots, network requests, and console logs after failures.
Test Runner: assertions, parallelism, retries, reports, and project matrices.
Locator: element selection by text, role, label, test id, and CSS.

Puppeteer is more like a lightweight browser control library. It is not bloated, its API is direct, and it is easy to embed in scripts, server-side jobs, and custom automation flows.

If you are building an enterprise-grade test system, Playwright’s tooling saves a lot of work. If you only need a Node.js script to convert webpages to PDFs or take scheduled screenshots, Puppeteer may be cleaner.

Where browser-harness fits

browser-harness is not the same kind of tool as Playwright or Puppeteer.

Playwright and Puppeteer mostly assume that humans write scripts. Engineers choose selectors, waiting conditions, assertions, and exception handling. They pursue determinism: the same script should produce the same result under the same page state.

browser-harness mostly assumes that an AI agent operates the browser. Its goal is not to provide a huge high-level API, but to connect to real Chrome through CDP and expose screenshots, coordinate clicks, DOM, network requests, and helpers to the agent. The agent can observe the page, decide the next step, add helpers when capabilities are missing, and turn site experience into skills.

That makes it better for open-ended tasks:

Log in to a backend and download invoices.
Fill a group of forms in an internal system.
Handle OA or SaaS pages that change often.
Explore a page according to a user goal instead of running a fixed script.
Give tools such as Claude Code and Codex CLI browser operation capability.

Three-way comparison

Dimension	Puppeteer	Playwright	browser-harness
Target user	Engineers	Engineers and test teams	AI Agent
Main goal	Control Chrome	Stable cross-browser automation	Let agents operate real browsers
Script style	Hand-written JS/TS automation	Scripts plus test framework	User gives a goal, agent executes steps
Element targeting	CSS, XPath, DOM API	Locator, text, role, CSS	Screenshots, coordinates, DOM, CDP
Waiting	More manual control	Strong auto-waiting	Agent observes and adjusts
Browser environment	Usually automated browser	Usually test browser	Often real Chrome
Best fit	Chrome scripts, screenshots, PDF, lightweight scraping	E2E tests, cross-browser validation, complex SPA	AI assistants, open web tasks, real-account workflows

Code feel

Puppeteer feels closer to directly controlling Chrome:

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  await page.goto('https://example.com');

  await page.waitForSelector('#submit-btn');
  await page.click('#submit-btn');

  await browser.close();
})();

Playwright emphasizes Locator and auto-waiting:

const { chromium } = require('playwright');

(async () => {
  const browser = await chromium.launch();
  const page = await browser.newPage();
  await page.goto('https://example.com');

  await page.locator('#submit-btn').click();

  await browser.close();
})();

browser-harness feels completely different. You usually do not write a full script. You give a goal inside an agent environment:

`1`	`Open the admin panel, download last month’s invoice, and organize it for reimbursement.`

The agent then repeatedly uses browser-harness to:

Take screenshots and understand the current page.
Click a coordinate or locate an element.
Enter text, upload files, and download files.
Decide how to close popups.
Add helper code when something is missing.
Turn reusable flows into domain skills.

This is not the style of traditional test scripts. It is the workflow of a browser agent.

How to choose

Choose Puppeteer when:

The project mainly runs in Node.js.
You only need Chrome or Chromium.
The task is screenshot, PDF generation, simple page scraping, or lightweight automation.
You want a simple API, fewer dependencies, and more manual control.
You rely deeply on Chrome DevTools Protocol.

Choose Playwright when:

You are building standard UI automation or E2E tests.
You need Chromium, Firefox, and WebKit coverage.
Your team’s main language may be Python, Java, or C#.
The page is a complex SPA with many asynchronous states and potential flaky tests.
You need codegen, Trace Viewer, test reports, and parallel testing.

Choose browser-harness when:

You are building or using AI agents.
You want the model to operate a real browser like a human.
The task steps are not fixed and require page-by-page judgment.
The target site changes often, or has many popups, iframes, and shadow DOM.
You want real web workflows handled by Claude Code, Codex CLI, or similar tools.

Conclusion

Playwright and Puppeteer are browser automation tools whose core goal is to let humans write reliable scripts. Puppeteer is lighter and closer to Chrome. Playwright is more complete and better for cross-browser testing and complex frontend applications.

browser-harness is a different direction. It is not designed to replace Playwright or Puppeteer for tests. It is designed to let AI agents control real browsers. It gives up some traditional script determinism in exchange for stronger adaptability in open-ended tasks.

So the answer is not to pick only one. Choose by task layer:

Test engineering: prefer Playwright.
Lightweight Chrome scripts: Puppeteer fits well.
AI agents doing work on the web: look at browser-harness.

References:

browser-use/browser-harness: https://github.com/browser-use/browser-harness
Playwright documentation: https://playwright.dev/
Puppeteer documentation: https://pptr.dev/
Chrome DevTools Protocol: https://chromedevtools.github.io/devtools-protocol/

What Is CloakBrowser? A More Realistic Browser for Playwright and Puppeteer

Tue, 19 May 2026 10:56:50 +0800

CloakHQ/CloakBrowser is an open source project for browser automation. It is not just a Playwright configuration file or a small JavaScript patch. The project is built around a custom Chromium binary, aiming to make browser fingerprints, WebGL, Canvas, audio, fonts, GPU, screen data, WebRTC, and network timing look closer to a normal browser environment.

Project URL: https://github.com/CloakHQ/CloakBrowser

At the time of writing, the GitHub API showed about 15k stars, Python as the main language, and an MIT license. The README positions it very directly: a Stealth Chromium launcher that can replace the default Playwright or Puppeteer browser launcher.

What Problem Does It Solve

Many automation scripts expose obvious automation signals when they run in a regular Headless Chromium environment, for example:

navigator.webdriver.
Headless user agent traces.
Unnatural plugin, font, screen, and GPU fingerprints.
CDP behavior that does not match real user input.
Temporary profiles without normal browsing traces.

CloakBrowser moves part of this work into the Chromium source and binary layer, instead of relying only on runtime configuration or JavaScript patches. For Playwright users, the API still feels close to familiar browser automation, but the underlying browser is replaced with the custom build provided by the project.

This type of tool is suitable for compliant automation testing, site compatibility checks, anti-abuse system self-testing, and agent browser environment experiments. It should not be used for unauthorized access, account abuse, bypassing platform risk controls, or violating service terms.

Basic Usage

Python installation:

`1`	`pip install cloakbrowser`

JavaScript / Node.js installation:

`1`	`npm install cloakbrowser playwright-core`

The Python example in the README looks close to Playwright:

from cloakbrowser import launch

browser = launch()
page = browser.new_page()
page.goto("https://protected-site.com")
browser.close()

The JavaScript usage is also straightforward:

import { launch } from 'cloakbrowser';

const browser = await launch();
const page = await browser.newPage();
await page.goto('https://protected-site.com');
await browser.close();

Browser Profile Manager

CloakBrowser also provides a Browser Profile Manager. It is meant for managing browser profiles, testing environments, and repeated automation tasks more conveniently.

`1`	`docker run -p 8080:8080 -v cloakprofiles:/data cloakhq/cloakbrowser-manager`

After starting it, open:

`1`	`http://localhost:8080`

The value of a profile manager is that the browser environment does not have to be a disposable temporary profile every time. For long-running tests, compatibility checks, and agent experiments, stable profiles are often easier to debug.

How It Differs From Regular Playwright

Regular Playwright focuses on reliable browser control. CloakBrowser focuses on making the browser environment itself look more natural.

In practice, the difference is:

Playwright provides the automation API.
CloakBrowser provides a custom browser runtime.
Playwright is suitable for general testing and automation.
CloakBrowser is more focused on realistic browser behavior and fingerprint consistency.

This does not mean CloakBrowser can magically solve all detection problems. Websites can still use behavior, frequency, account reputation, network environment, and business rules to judge risk.

What To Watch Out For

First, compliance matters. A more realistic automation environment does not mean unrestricted use. Automated access should respect authorization, rate limits, robots or platform rules, and service terms.

Second, the project depends on a custom Chromium build. Teams should pay attention to version compatibility, security updates, and whether the binary source is acceptable for production use.

Third, realistic browser behavior is only one part of the picture. If the script performs unnatural operations, sends requests too frequently, or uses accounts in abnormal ways, the result will still be risky.

Who It Is For

CloakBrowser is more suitable for developers and teams already using Playwright, Puppeteer, browser agents, QA automation, or web compatibility testing. It is less suitable for users who just want a no-code browser automation product.

Summary

CloakBrowser is interesting because it moves browser automation from “just control a headless browser” toward “use a browser environment closer to real users.” For testing, agent experiments, and controlled research, it is worth watching. For real-world use, the important boundary is still compliance, authorization, and risk control.

ai-goofish-monitor: An Open-Source AI Monitoring System for Goofish Listings

Sun, 17 May 2026 17:24:03 +0800

ai-goofish-monitor is an open-source Goofish product monitoring system from Usagi-org.

Its goal is clear: automate Goofish search, filtering, product analysis, result logging, and notifications, so users can find matching second-hand listings faster. The project uses Playwright for browser automation and connects to image-capable AI models to judge product information more intelligently.

Project link: https://github.com/Usagi-org/ai-goofish-monitor

The Short Version

ai-goofish-monitor is closer to a “Goofish purchasing intelligence dashboard” than a simple keyword alert script.

It has several notable traits:

A complete web admin UI for managing tasks, accounts, AI criteria, logs, and results.
Concurrent multi-task monitoring, where each task can define keywords, price range, filters, and AI Prompt.
Playwright-based page automation, useful for scenarios that require login state and page interaction.
AI-based product judgment, not just keyword matching.
Notifications through ntfy.sh, WeCom, Bark, Telegram, Webhook, and other channels.
Cron scheduling, multi-account management, proxy rotation, retry handling, and Docker deployment.

It fits users who often search Goofish for specific items, such as second-hand electronics, cameras, GPUs, hard drives, game consoles, musical instruments, appliances, and collectibles. But it is not an “automatic bargain hunter.” Goofish search results change, login states may expire, and platform risk controls can affect automation stability. Treat it as an assisted filtering tool, not a replacement for human judgment.

What Problem It Solves

Finding second-hand products on Goofish often has several pain points:

There are too many listings to browse manually.
Titles and descriptions are inconsistent, so keywords can miss or misclassify listings.
Good prices appear briefly and may be gone by the time you see them.
The same product may differ by region, price, condition, and seller.
Low-priced listings can include accessories, damaged goods, refurbished items, or misleading titles.
Watching multiple keywords continuously is hard to sustain manually.

Basic keyword alerts solve only part of this. Searching for “ThinkPad X1” may mix in accessories, broken screens, empty boxes, or disassembled parts. Searching for “Sony A7C” may return lens bundles, rentals, clickbait titles, or abnormal prices.

ai-goofish-monitor’s idea is to use automation to collect candidate listings, then let AI apply your criteria, and finally push the results worth attention.

Core Features

The project README lists a fairly complete feature set:

Visual web management: task management, account management, AI criteria editing, run logs, and result browsing.
AI-driven workflow: create tasks with natural language and analyze products with multimodal models.
Concurrent tasks: each task can define keywords, prices, filters, and AI Prompt independently.
Advanced filters: free shipping, newly listed time range, and province / city / district filtering.
Instant notifications: ntfy.sh, WeCom, Bark, Telegram, Webhook, and more.
Scheduled execution: Cron-based periodic tasks.
Account and proxy rotation: multi-account management, task-account binding, proxy pool rotation, and retry handling.
Docker deployment: containerized deployment support.

Together, these cover the full chain from creating a monitoring task to receiving a matching alert.

Workflow

A typical workflow looks like this:

Deploy the service and open the Web UI.
Import Goofish account login state.
Create a monitoring task.
Set keywords, price range, region, newly listed window, and other filters.
Write criteria or let AI generate them.
Run the task in real-time or on a schedule.
Playwright opens pages and extracts product information.
AI checks title, description, images, and Prompt against your needs.
Matching results are written to SQLite.
The system sends notifications through configured channels.
You review results, logs, and price history in the Web UI.

AI matters most at step 8. It can understand natural language criteria like “good condition, reasonable price, no accessories, no repaired units, preferably local pickup,” which is more flexible than simple keyword rules.

Docker Deployment

The project recommends Docker deployment:

git clone https://github.com/Usagi-org/ai-goofish-monitor && cd ai-goofish-monitor
cp .env.example .env
vim .env
docker compose up -d
docker compose logs -f app
docker compose down

The default Web UI address is:

`1`	`http://127.0.0.1:8000`

The official image is:

`1`	`ghcr.io/usagi-org/ai-goofish:latest`

If the image pulls slowly, the README also gives an accelerated mirror example:

1
2
3

docker pull ghcr.nju.edu.cn/usagi-org/ai-goofish:latest
docker tag ghcr.nju.edu.cn/usagi-org/ai-goofish:latest ghcr.io/usagi-org/ai-goofish:latest
docker compose up -d

The Docker image includes Chromium, so the host does not need an extra browser. Default persistent directories include:

data/: main SQLite storage for tasks, results, and price history.
state/: login-state cookie files.
prompts/: task prompts.
logs/: runtime logs.
images/: product images and temporary task image folders.

If you change SERVER_PORT in .env, also update the port mapping in docker-compose.yaml.

Minimum Configuration

The minimum configuration mainly covers the AI model and Web UI login:

OPENAI_API_KEY=your_api_key
OPENAI_BASE_URL=your_openai_compatible_base_url
OPENAI_MODEL_NAME=your_multimodal_model
WEB_USERNAME=admin
WEB_PASSWORD=change_me

The first three are required for AI model access:

OPENAI_API_KEY: model API key.
OPENAI_BASE_URL: OpenAI-compatible endpoint.
OPENAI_MODEL_NAME: model name that supports image input.

WEB_USERNAME and WEB_PASSWORD are used for Web UI login. The README mentions the default credentials admin/admin123; change them in production.

First Use

The first-use flow is roughly:

Open http://127.0.0.1:8000.
Log in to the Web UI.
Go to Goofish account management.
Use the provided Chrome extension to export Goofish login-state JSON.
Paste the login state into the system.
The state file is saved to state/, for example state/acc_1.json.
Return to task management, create a task, and bind an account.
Run the task and check results.

The key part is login state. Goofish does not provide a standard open API for arbitrary third-party scraping, so the project uses browser login state to simulate normal page access. Expired login state, risk controls, captchas, and account anomalies can all affect task execution.

AI Tasks and Keyword Tasks

The project supports two task creation modes.

The first is AI判断.

You can enter detailed requirements, and the system asynchronously generates analysis criteria. This fits complex needs, for example:

Only the main unit, no accessories.
Alert only when the price is clearly below market.
Good condition, with no water damage, repair, or hidden defects in the description.
Prefer local listings and face-to-face pickup.
Images should show serial number, packaging, or key accessories.

The second is 关键词判断.

This is closer to traditional rule-based monitoring: create tasks directly from keywords, prices, regions, and other conditions without AI generation. It fits simple rules where some false positives are acceptable.

In practice, you can mix both: keywords handle initial filtering, AI reduces false positives.

What the Web UI Does

The Web UI is a major difference between this project and ordinary scripts.

The task management page can configure:

AI-created tasks.
Keyword rules.
Price ranges.
Newly listed windows.
Region filters.
Account binding.
Scheduling rules.

The account management page can:

Import Goofish account login state.
Update login state.
Delete accounts.
Assign accounts to tasks.
Let the system choose accounts automatically.

Results and logs pages can:

View matching products.
Export results.
Search history.
Inspect task execution.
Troubleshoot login expiration, risk controls, and AI call issues.

The system settings page can:

View system status.
Edit Prompt.
Adjust proxy and rotation configuration.

For long-term monitoring, the Web UI is important. Without it, many tasks quickly make configuration, logs, results, and notifications hard to maintain.

Data Storage

The current online primary storage is SQLite, with the default path:

`1`	`data/app.sqlite3`

Docker mounts the SQLite main database by default:

`1`	`./data:/app/data`

On startup, the app creates tables automatically and tries to import historical data once from old config.json, jsonl/, and price_history/.

Note that state/, prompts/, logs/, and images/ remain filesystem directories and are not stored in SQLite. Product images are temporarily saved to directories like:

`1`	`images/task_images_<task_name>/`

They are cleaned up by default after the task ends.

This structure fits personal or small-team deployments: SQLite is lightweight and easy to migrate, while files keep login state, images, and logs easy to inspect.

Notification Channels

The project supports multiple notification channels. Common configuration items include:

NTFY_TOPIC_URL
GOTIFY_URL / GOTIFY_TOKEN
BARK_URL
WX_BOT_URL
TELEGRAM_BOT_TOKEN / TELEGRAM_CHAT_ID / TELEGRAM_API_BASE_URL
WEBHOOK_*

Notifications are central to the experience. If a monitor only writes results to a backend, users still need to keep checking the page. With push notifications, matching listings reach the user immediately.

A practical setup is to tier notifications by item value:

Normal keyword hits are written only to the backend.
High-confidence AI results are pushed to the phone.
High-value items are pushed to WeCom or Telegram.
Enable more logs during debugging, then reduce noise after stabilization.

Developer Run

Without Docker, local development requires:

Python 3.10+
Node.js + npm
Playwright CLI
Chromium or Chrome / Edge browser

Basic commands:

1
2
3

git clone https://github.com/Usagi-org/ai-goofish-monitor
cd ai-goofish-monitor
cp .env.example .env

One-command startup:

1
2

chmod +x start.sh
./start.sh

start.sh checks Playwright CLI and browser conditions, installs dependencies, builds the frontend, copies build artifacts, and starts the backend.

Start the backend manually:

`1`	`python -m src.app`

Or:

`1`	`uvicorn src.app:app --host 0.0.0.0 --port 8000 --reload`

Frontend development:

1
2
3

cd web-ui
npm install
npm run dev

Testing and build:

1
2

PYTEST_DISABLE_PLUGIN_AUTOLOAD=1 pytest
cd web-ui && npm run build

Who It Fits

ai-goofish-monitor fits users who:

Frequently watch Goofish for specific models.
Want to monitor second-hand electronics, cameras, game devices, hardware parts, and similar goods.
Want to automate “keyword search + manual screening.”
Have an OpenAI-compatible model API and accept AI judgment costs.
Are comfortable with Docker or basic command-line deployment.
Need matching results pushed to phone, WeCom, or Telegram.

It is less suitable if you:

Know nothing about deployment and only want a ready-to-use app.
Do not want to handle login state, captchas, or account risk controls.
Need official authorization and strongly compliant data APIs.
Want large-scale high-frequency platform scraping.
Expect AI to automatically judge trading risk and place orders for you.

Risks and Boundaries

Tools like this need clear boundaries.

First, follow platform rules.

Goofish has its own terms, risk controls, and account security mechanisms. Automation may trigger restrictions. Do not scrape at high frequency, bypass risk controls, harass sellers, bulk-collect private information, or disrupt platform order.

Second, protect account login state.

Files in state/ are login-state cookie files. They are effectively account access credentials. Do not commit them to Git, and do not put them on untrusted servers. If the server is exposed to the public internet, change the default Web UI password and place it behind a VPN, reverse-proxy authentication, or an internal network.

Third, AI judgment is not a factual guarantee.

AI can reduce false positives, but it cannot guarantee product authenticity, seller trustworthiness, reasonable pricing, or transaction safety. You still need to review product details, seller reputation, chat history, shipping method, and payment process.

Fourth, watch cost.

If every candidate listing is analyzed by a multimodal model, costs can rise quickly. Use keyword, price, and region filters first, then send a smaller candidate set to AI.

Fifth, protect privacy.

Product screenshots, chat-related content, account state, and notification content may all contain sensitive information. Protect notification Webhooks, log directories, and databases carefully.

Difference from Ordinary Scripts

Ordinary Goofish monitoring scripts usually do three things:

Search keywords.
Check prices.
Send notifications.

ai-goofish-monitor goes further:

Manage tasks and accounts through Web UI.
Express complex buying criteria with AI Prompt.
Use multimodal models to inspect product images and descriptions.
Store results and price history in SQLite.
Use log pages to diagnose task failures.
Improve stability through proxy rotation and multi-account mechanisms.
Support long-running schedules with Cron.

Because it does more, it also costs more to deploy and maintain. For normal users, Docker is the easiest path. For developers, the Web UI, FastAPI, Playwright, and SQLite structure is also friendly for secondary development.

How to Use It

A practical approach is to start with small tasks.

For example, if you want a second-hand camera, create a task like this:

Keywords: A7C, 索尼 A7C
Price range: set an upper limit based on market price
Region: prefer same province or local city
Newly listed window: last day or last few hours
AI criteria: exclude lens-only listings, repaired units, obvious accessories; pay attention to shutter count and condition
Notification: push only results that pass AI judgment

After it runs stably, gradually add more tasks. Do not start with dozens of keywords, multiple accounts, and high-frequency Cron. First check login stability, false-positive rate, AI cost, and notification noise, then tune parameters.

Summary

ai-goofish-monitor moves Goofish monitoring from a “keyword script” to a manageable AI monitoring system. It uses Playwright for page automation, AI for complex judgment, Web UI for tasks and results, SQLite for storage, and multiple notification channels for delivery.

It is best for individuals or small teams monitoring specific products, especially second-hand electronics, hardware, and cameras where prices fluctuate, timing matters, and descriptions are noisy.

But it must be used carefully: protect login state, change default passwords, keep scraping frequency restrained, review AI results manually, and respect platform rules and privacy boundaries. As an assisted filtering tool, it can be valuable. As a fully automated trading system, it is easy to overestimate.

References:

Playwright CLI Video Recording: Recording, Chapter Markers, Overlays, and Debugging Tradeoffs

Wed, 15 Apr 2026 08:22:45 +0800

If you want to record browser automation sessions as video for debugging, documentation, or proof of work, Playwright CLI already provides a fairly direct workflow. It produces WebM video using the VP8/VP9 codec.

This article follows the official video-recording reference and focuses on the parts that matter most in practice: the basic recording flow, chapter markers, full hero-script recording, the Overlay API, and the difference between video and tracing. The command lines, code snippets, and parameter details are preserved from the reference.

01 Basic Recording Flow

The basic pattern is simple: open the browser, start recording, perform actions, then stop and save.

# Open browser first
playwright-cli open

# Start recording
playwright-cli video-start demo.webm

# Add a chapter marker for section transitions
playwright-cli video-chapter "Getting Started" --description="Opening the homepage" --duration=2000

# Navigate and perform actions
playwright-cli goto https://example.com
playwright-cli snapshot
playwright-cli click e1
# Add another chapter
playwright-cli video-chapter "Filling Form" --description="Entering test data" --duration=2000
playwright-cli fill e2 "test input"

# Stop and save
playwright-cli video-stop

These commands already cover the most common recording flow. video-chapter is useful for inserting chapter cards between stages so the final video is easier to follow.

02 Best Practices

1. Use Descriptive Filenames

If the video is meant for other people or for later review, the filename should include enough context to make it understandable at a glance.

1
2
3

# Include context in filename
playwright-cli video-start recordings/login-flow-2024-01-15.webm
playwright-cli video-start recordings/checkout-test-run-42.webm

2. Record Entire Hero Scripts

The official recommendation is that when a video is for a user or serves as proof of work, it is best to turn the scenario into a code snippet and execute it with run-code. That gives you better control over pacing, pauses, and annotations in the video. The reference also notes that Playwright now includes APIs designed specifically for this kind of recording flow.

The suggested process is:

First perform the scenario with the CLI and note all locators and actions. You will need those locators later if you want their bounding boxes for highlight overlays.
Create a dedicated script file for the video and write it in the style shown below. Use pressSequentially with delay for smoother typing, and add pauses where they feel natural.
Use playwright-cli run-code --filename your-script.js.

Important: Overlays are pointer-events: none — they do not interfere with page interactions. You can safely keep sticky overlays visible while clicking, filling, or performing any actions on the page.

async page => {
  await page.screencast.start({ path: 'video.webm', size: { width: 1280, height: 800 } });
  await page.goto('https://demo.playwright.dev/todomvc');
  // Show a chapter card — blurs the page and shows a dialog.
  // Blocks until duration expires, then auto-removes.
  // Use this for simple use cases, but always feel free to hand-craft your own beautiful
  // overlay via await page.screencast.showOverlay().
  await page.screencast.showChapter('Adding Todo Items', {
    description: 'We will add several items to the todo list.',
    duration: 2000,
  });
  // Perform action
  await page.getByRole('textbox', { name: 'What needs to be done?' }).pressSequentially('Walk the dog', { delay: 60 });
  await page.getByRole('textbox', { name: 'What needs to be done?' }).press('Enter');
  await page.waitForTimeout(1000);

  // Show next chapter
  await page.screencast.showChapter('Verifying Results', {
    description: 'Checking the item appeared in the list.',
    duration: 2000,
  });
  // Add a sticky annotation that stays while you perform actions.
  // Overlays are pointer-events: none, so they won't block clicks.
  const annotation = await page.screencast.showOverlay(`
    <div style="position: absolute; top: 8px; right: 8px;
      padding: 6px 12px; background: rgba(0,0,0,0.7);
      border-radius: 8px; font-size: 13px; color: white;">
      ✓ Item added successfully
    </div>
  `);
  // Perform more actions while the annotation is visible
  await page.getByRole('textbox', { name: 'What needs to be done?' }).pressSequentially('Buy groceries', { delay: 60 });
  await page.getByRole('textbox', { name: 'What needs to be done?' }).press('Enter');
  await page.waitForTimeout(1500);

  // Remove the annotation when done
  await annotation.dispose();
  // You can also highlight relevant locators and provide contextual annotations.
  const bounds = await page.getByText('Walk the dog').boundingBox();
  await page.screencast.showOverlay(`
    <div style="position: absolute;
      top: ${bounds.y}px;
      left: ${bounds.x}px;
      width: ${bounds.width}px;
      height: ${bounds.height}px;
      border: 1px solid red;">
    </div>
    <div style="position: absolute;
      top: ${bounds.y + bounds.height + 5}px;
      left: ${bounds.x + bounds.width / 2}px;
      transform: translateX(-50%);
      padding: 6px;
      background: #808080;
      border-radius: 10px;
      font-size: 14px;
      color: white;">Check it out, it is right above this text
    </div>
  `, { duration: 2000 });
  await page.screencast.stop();
}

The value of this script is not only that it records the flow, but that it makes the video easier to understand: chapter cards handle transitions, pressSequentially makes typing look natural, and showOverlay adds explanation, highlights, and context.

The reference closes this section with a short reminder: Embrace creativity, overlays are powerful.

03 Overlay API Summary

When recording video, the Overlay API is especially useful for section transitions, local callouts, and sticky annotations. The official summary is:

Method	Use Case
`page.screencast.showChapter(title, { description?, duration?, styleSheet? })`	Full-screen chapter card with blurred backdrop — ideal for section transitions
`page.screencast.showOverlay(html, { duration? })`	Custom HTML overlay — use for callouts, labels, highlights
`disposable.dispose()`	Remove a sticky overlay added without duration
`page.screencast.hideOverlays()` / `page.screencast.showOverlays()`	Temporarily hide/show all overlays

If your goal is to turn automation into a video people can comfortably watch, this API set is one of the most valuable pieces to learn first.

04 Tracing vs Video

The official documentation makes the difference between the two very clear:

Feature	Video	Tracing
Output	WebM file	Trace file (viewable in Trace Viewer)
Shows	Visual recording	DOM snapshots, network, console, actions
Use case	Demos, documentation	Debugging, analysis
Size	Larger	Smaller

A simple way to think about it:

video is better for demos, delivery, and reviewing what a user would see
tracing is better for debugging, inspecting action details, and analyzing execution context

They are not replacements for each other. Each serves a different purpose.

05 Limitations

The reference also points out two practical limitations:

Recording adds slight overhead to automation
Large recordings can consume significant disk space

So while video recording is very useful, it does add some runtime overhead, and longer recordings can grow large on disk.

06 Quick Summary

If you only want the essentials, remember these points:

video-start / video-stop are the core commands for recording
video-chapter adds section transitions and makes demos easier to follow
More advanced recording scenarios are best written as scripts and executed with run-code
showOverlay and showChapter can significantly improve video readability
video is best for demos, while tracing is best for debugging

If your workflow already includes automation demos, acceptance evidence, or proof-of-work recordings, video recording is a very worthwhile part of Playwright CLI to add.

References

Playwright CLI video-recording reference: https://github.com/microsoft/playwright-cli/blob/main/skills/playwright-cli/references/video-recording.md
Playwright CLI project homepage: https://github.com/microsoft/playwright-cli

Playwright CLI Session Management: Multiple Browser Sessions, Isolation, Persistence, and Cleanup

Wed, 15 Apr 2026 08:15:12 +0800

If you use Playwright CLI for automation, you will quickly run into a practical question: can you open multiple browser sessions at the same time without them interfering with each other? The answer is yes, and Playwright CLI already makes this mechanism quite straightforward.

Following the official session-management reference, this article focuses on its most practical pieces: named sessions, session isolation, persistent profiles, concurrent patterns, and common cleanup commands. The command lines and command block explanations are preserved from the reference content.

01 Named Browser Sessions

The official recommendation is to use the -s parameter to isolate different browser contexts:

# Browser 1: Authentication flow
playwright-cli -s=auth open https://app.example.com/login

# Browser 2: Public browsing (separate cookies, storage)
playwright-cli -s=public open https://example.com

# Commands are isolated by browser session
playwright-cli -s=auth fill e1 "user@example.com"
playwright-cli -s=public snapshot

The key point here is that different session names map to different browser contexts. You can use auth for the sign-in flow and public for anonymous browsing, and they will not share cookies or local state.

02 What Does Browser Session Isolation Separate?

Each browser session maintains the following items independently:

Cookies
LocalStorage / SessionStorage
IndexedDB
Cache
Browsing history
Open tabs

That means if you sign in to a site in the auth session, it will not automatically affect the public session. This is especially important for multi-account testing, login-state verification, and anonymous-vs-authenticated comparisons.

The official documentation groups the most commonly used session-management commands together:

# List all browser sessions
playwright-cli list

# Stop a browser session (close the browser)
playwright-cli close                 # stop the default browser
playwright-cli -s=mysession close   # stop a named browser

# Stop all browser sessions
playwright-cli close-all

# Forcefully kill all daemon processes (for stale/zombie processes)
playwright-cli kill-all

# Delete browser session user data (profile directory)
playwright-cli delete-data              # delete default browser data
playwright-cli -s=mysession delete-data # delete named browser data

You can think of them as three kinds of operations:

list: see which sessions currently exist
close / close-all / kill-all: stop sessions or clean up stuck browser processes
delete-data: remove the user data directory for a specific session

If you just want to close a browser, close is usually the first choice. If leftover or zombie processes have already appeared, kill-all is the better fit.

04 Set a Default Session with an Environment Variable

If you do not want to repeat -s=mysession on every command, the official docs also provide an environment-variable approach:

1
2

export PLAYWRIGHT_CLI_SESSION="mysession"
playwright-cli open example.com  # Uses "mysession" automatically

After that, when you do not explicitly specify -s, the command will use mysession as the default browser session.

05 Common Pattern: Concurrent Scraping

The reference gives a very typical concurrent-scraping example:

#!/bin/bash
# Scrape multiple sites concurrently

# Start all browsers
playwright-cli -s=site1 open https://site1.com &
playwright-cli -s=site2 open https://site2.com &
playwright-cli -s=site3 open https://site3.com &
wait

# Take snapshots from each
playwright-cli -s=site1 snapshot
playwright-cli -s=site2 snapshot
playwright-cli -s=site3 snapshot

# Cleanup
playwright-cli close-all

This pattern works well when you want to open multiple sites at once, capture each page state, and then clean everything up together. Because each site runs in an independent session, they do not contaminate each other’s local state.

06 Common Pattern: A/B Test Sessions

Another common scenario is comparing different experiment variants at the same time:

# Test different user experiences
playwright-cli -s=variant-a open "https://app.com?variant=a"
playwright-cli -s=variant-b open "https://app.com?variant=b"

# Compare
playwright-cli -s=variant-a screenshot
playwright-cli -s=variant-b screenshot

This style is great for A/B page comparisons because the two variants run in separate sessions, making screenshots and state checks easier to manage independently.

07 Persisting Browser Profiles

The official documentation specifically points out that browser profiles are stored only in memory by default.

If you want to persist a browser profile to disk, add --persistent when running open:

# Use persistent profile (auto-generated location)
playwright-cli open https://example.com --persistent

# Use persistent profile with custom directory
playwright-cli open https://example.com --profile=/path/to/profile

This capability is useful when you need to reuse login state, local cache, or an extension-debugging environment over the long term. When repeatedly debugging the same site, a persistent profile is often much more efficient than starting from scratch every time.

08 The Default Browser Session

If -s is not explicitly provided, the command uses the default browser session:

# These use the same default browser session
playwright-cli open https://example.com
playwright-cli snapshot
playwright-cli close  # Stops default browser

In other words, commands without -s are executed continuously within the same default session.

In addition to the session name, the official docs also show several common startup configuration patterns:

# Open with config file
playwright-cli open https://example.com --config=.playwright/my-cli.json

# Open with specific browser
playwright-cli open https://example.com --browser=firefox

# Open in headed mode
playwright-cli open https://example.com --headed

# Open with persistent profile
playwright-cli open https://example.com --persistent

These parameters can be combined with session management. For example, you can make one named session always run in firefox, or make a specific session always launch in headed mode for easier manual inspection.

10 Best Practices from the Official Docs

The reference lists three practical best practices.

1. Use Meaningful Session Names

# GOOD: Clear purpose
playwright-cli -s=github-auth open https://github.com
playwright-cli -s=docs-scrape open https://docs.example.com

# AVOID: Generic names
playwright-cli -s=s1 open https://github.com

Session names should ideally communicate their purpose directly. Names like github-auth and docs-scrape make later script maintenance much clearer.

2. Clean Up Promptly After Use

# Stop browsers when done
playwright-cli -s=auth close
playwright-cli -s=scrape close

# Or stop all at once
playwright-cli close-all

# If browsers become unresponsive or zombie processes remain
playwright-cli kill-all

If you do not close the browser after a task finishes, the session and background processes will remain. That may not seem serious in the short term, but once tasks pile up, the environment can become messy very quickly.

3. Remove Stale Browser Data

1
2

# Remove old browser data to free disk space
playwright-cli -s=oldsession delete-data

When some old sessions are no longer needed, deleting their data directories saves disk space and also helps avoid accidentally reusing outdated state later.

11 Quick Summary

If you only want the essentials, remember these points:

-s=<name> creates and uses an independent browser session
Different sessions isolate cookies, different kinds of storage, cache, history, and tabs
close-all is useful for unified shutdown, while kill-all is useful for cleaning up abnormal leftover processes
--persistent writes the profile to disk and is useful for long-term state reuse
Session names should be meaningful, and old data should be cleaned up regularly

If your workflow already includes reused login states, parallel multi-account work, A/B comparisons, or batch scraping, then session management is basically one of the most worthwhile pieces of Playwright CLI to learn first.

References

Playwright CLI session-management reference: https://github.com/microsoft/playwright-cli/blob/main/skills/playwright-cli/references/session-management.md
Playwright CLI project homepage: https://github.com/microsoft/playwright-cli

Playwright CLI storage state: Save Login Sessions, Read Cookies, and Local Storage

Tue, 14 Apr 2026 22:19:55 +0800

If you use Playwright CLI for browser automation, storage state is one of the most useful features. Its job is simple: save the current login session and local browser state so you can reuse them later instead of logging in every time.

01 Save the current storage state

The most common workflow is to log in once, then export the current state to a file.

`1`	`playwright-cli storage-state save auth.json`

This command saves the current browser context state to auth.json. If you want to reuse a login session later, this is usually the first step.

02 Load an existing storage state

Once you already have a state file, you can load it directly at startup.

`1`	`playwright-cli --storage-state auth.json`

It launches the browser context with the state stored in auth.json. The usual purpose is to skip repeated login and jump straight into a signed-in environment.

03 View current cookies

If you only want to check which cookies exist in the current session, you can inspect them directly.

`1`	`playwright-cli cookies`

This command lists the cookies in the current context. It is useful when checking whether the login state exists or whether cookies were written successfully.

04 Set cookies

If you already have cookie data, you can inject it directly as well.

`1`	`playwright-cli cookies set '[{"name":"session","value":"abc","domain":"example.com","path":"/"}]'`

This is useful for auth debugging, reproducing a specific session, or injecting cookie conditions before a script runs.

05 Read localStorage

Some sites store login-related or frontend state not only in cookies, but also in localStorage.

`1`	`playwright-cli local-storage`

This command shows the localStorage content of the current page. It is especially useful when a page looks logged in but still behaves incorrectly.

06 Write localStorage

If you need to simulate specific frontend state, you can set it directly.

`1`	`playwright-cli local-storage set token abc123`

It writes the given key and value into localStorage. Common uses include injecting a token, a preference, or a frontend flag.

07 Read sessionStorage

sessionStorage is useful for checking temporary state tied to the current session.

`1`	`playwright-cli session-storage`

This command outputs the current page’s sessionStorage. If a page flow depends on one-time session data, this is a good place to inspect it.

08 Write sessionStorage

When needed, you can also set sessionStorage manually.

`1`	`playwright-cli session-storage set key value`

It is useful for reproducing page behavior that depends on temporary state, or for filling in fields required by an initialization step.

09 View IndexedDB

For heavier web apps, the most important local data may actually live in IndexedDB.

`1`	`playwright-cli indexed-db`

This command lets you inspect the current page’s IndexedDB data. It is worth checking first when you are dealing with complex SPAs, offline cache, or app-like local databases.

10 A practical workflow

If your goal is simply to reuse a login session reliably, the most practical flow is usually this:

Open the site and complete login manually.
Save the state with this command:

`1`	`playwright-cli storage-state save auth.json`

Load it directly in later runs:

`1`	`playwright-cli --storage-state auth.json`

If the page still behaves incorrectly after loading, continue by checking:

playwright-cli cookies
playwright-cli local-storage
playwright-cli session-storage
playwright-cli indexed-db

That sequence covers most cases where the restored state is incomplete.

11 What to watch out for

Three points matter most:

A storage state file is sensitive data. It may contain login cookies or tokens, so do not commit it casually.
Restoring cookies alone may not be enough. Many modern sites also depend on localStorage, sessionStorage, or IndexedDB.
State files do not stay valid forever. After cookie expiration, account changes, or environment changes, you usually need to generate them again.

12 Quick summary

If you only remember one sentence:

Playwright CLI storage state means saving the browser’s current state and reusing it in later tasks.

In practice, the most useful commands are these:

playwright-cli storage-state save auth.json
playwright-cli --storage-state auth.json
playwright-cli cookies
playwright-cli local-storage
playwright-cli session-storage
playwright-cli indexed-db

Save first, then load; if something still looks wrong, inspect cookies and the different local storage layers one by one. That is the most practical part of this reference.

References

Playwright CLI storage-state reference: https://github.com/microsoft/playwright-cli/blob/main/skills/playwright-cli/references/storage-state.md
Playwright CLI project page: https://github.com/microsoft/playwright-cli

Getting Started with Playwright CLI: Installation, Skills, Sessions, and Essential Commands

Sun, 12 Apr 2026 14:36:58 +0800

If you have been using Claude Code, GitHub Copilot, or other coding agents for browser automation, microsoft/playwright-cli is a tool worth watching. It is not the traditional kind of browser helper meant mainly for humans typing commands by hand. Instead, it is a Playwright CLI designed for coding agents, with an emphasis on lower token overhead, a lighter command interface, and integration with Skills-based workflows.

From the official README, the core idea behind Playwright CLI is very clear: compared with MCP, which can push large tool schemas and page structure into the model context, the CLI approach is more compact and better suited for agent workflows that constantly switch between large codebases, tests, and browser automation.

01 What Playwright CLI is

playwright-cli is an open-source Playwright command-line tool from Microsoft. The official description is “CLI for common Playwright actions.” It is mainly used for tasks like these:

Opening pages and driving the browser
Recording and generating Playwright code
Capturing page snapshots to get element references
Taking screenshots and exporting PDFs
Working with coding agents for test automation and web interaction

The current GitHub README is very explicit about its positioning: if you are using coding agents, the CLI is often a better fit than Playwright MCP; if you need persistent state, richer introspection, and longer-running agentic loops, MCP still has its place.

In other words, Playwright CLI feels more like a browser automation interface built for AI coding assistants, not just a tool for engineers to click around manually.

02 Where it stands out

1. It fits agent workflows better

The official README lists Token-efficient as a key feature. It does not force full-page data into the LLM context. Instead, it lets the agent operate the browser through shorter and more focused commands.

That matters a lot for coding agents. In real projects, an agent is not only driving the browser. It also has to read code, edit files, run tests, and inspect logs. If the browser interface itself consumes too much context, the overall workflow becomes less efficient.

2. It works well with Skills

The README specifically highlights playwright-cli install --skills. That shows Microsoft is not treating it as just another shell utility, but as something that can be consumed directly by Claude Code, GitHub Copilot, and similar agents through a Skills-based workflow.

If your setup already relies on Skills, Playwright CLI should slot in naturally.

3. Session management is fairly complete

Playwright CLI supports sessions. By default, the browser profile stays in memory, so cookies and storage state are preserved across multiple CLI calls within the same session. If you add --persistent, the profile can be saved to disk and reused across browser restarts.

That makes it much more practical than tools that simply open a browser for one command and then throw everything away. It is also a better fit for long debugging cycles and longer-running agent flows.

4. It includes a visual monitoring dashboard

The README provides playwright-cli show, which opens a dashboard for observing and controlling all running browser sessions. This is especially useful when an agent is running automation in the background, because you can step in, inspect progress, and help with debugging instead of flying blind.

03 Installation and requirements

According to the current GitHub README, the basic requirements for Playwright CLI are:

Node.js 18 or newer
Claude Code, GitHub Copilot, or another coding agent

The installation commands are:

1
2

npm install -g @playwright/cli@latest
playwright-cli --help

There is one easy mistake worth calling out:

The officially recommended package right now is @playwright/cli
Do not confuse it with the old deprecated npm package playwright-cli

So the package you actually want is the scoped package, not the older historical one.

04 How to start using it

1. Install skills

If you want a coding agent to use Playwright CLI directly, the official recommendation is to install the skills first:

`1`	`playwright-cli install --skills`

The README explicitly says that Claude Code, GitHub Copilot, and similar tools will use the locally installed skills.

2. Let the agent call the CLI directly

If you do not want to handle Skills first, you can also let the agent read the CLI help output directly:

1
2

Test the "add todo" flow on https://demo.playwright.dev/todomvc using playwright-cli.
Check playwright-cli --help for available commands.

The README calls this “Skills-less operation.” The idea is that even without preinstalled skills, the CLI can still describe itself well enough for an agent to use it.

3. Try a minimal flow manually

The README includes a TodoMVC example that works very well as a first hands-on demo:

playwright-cli open https://demo.playwright.dev/todomvc/ --headed
playwright-cli type "Buy groceries"
playwright-cli press Enter
playwright-cli type "Water flowers"
playwright-cli press Enter
playwright-cli check e21
playwright-cli check e35
playwright-cli screenshot

This sequence is useful because it quickly shows how Playwright CLI works in practice:

open opens the page
type and press handle text input
check uses an element reference to toggle checkboxes
screenshot saves the result

05 `--headed`, sessions, and the monitoring dashboard

`--headed`

Playwright CLI is headless by default. If you want to see the browser window directly, you need to pass --headed when using open:

`1`	`playwright-cli open https://playwright.dev --headed`

This is especially helpful when debugging selectors, login flows, or any interaction that is easier to inspect visually.

sessions

The official README places a lot of emphasis on sessions. You can use different sessions to isolate different projects or sites:

1
2
3

playwright-cli open https://playwright.dev
playwright-cli -s=example open https://example.com --persistent
playwright-cli list

If you are letting an agent run over a longer period, you can also pass the session through an environment variable:

`1`	`PLAYWRIGHT_CLI_SESSION=todo-app claude .`

Useful session management commands include:

1
2
3

playwright-cli list
playwright-cli close-all
playwright-cli kill-all

In practice:

list shows all sessions
close-all closes all browsers gracefully
kill-all forcefully terminates all browser processes

Monitoring dashboard

If you want to see what the agent is actually doing in the browser, you can run:

`1`	`playwright-cli show`

According to the README, this dashboard has two main views:

Session grid: shows active sessions by workspace, with live preview, URL, and page title
Session detail: shows a live view of a selected session and lets you take over mouse and keyboard input

That means Playwright CLI is not only usable from the command line. It also has a fairly mature observability layer.

06 Which commands are worth memorizing first

If this is your first time using Playwright CLI, you do not need to memorize every command up front. These are the core ones worth learning first:

Pages and interaction

playwright-cli open [url]
playwright-cli goto <url>
playwright-cli click <ref>
playwright-cli fill <ref> <text>
playwright-cli type <text>
playwright-cli hover <ref>
playwright-cli press <key>

Getting page structure

playwright-cli snapshot
playwright-cli snapshot <ref>
playwright-cli snapshot --depth=N
playwright-cli eval <func> [ref]

snapshot is especially important because many later operations depend on element references stored as ref. In practice, you usually capture a snapshot first, then use the returned element identifiers for clicking, filling, checking, or taking screenshots.

Saving output

1
2

playwright-cli screenshot
playwright-cli pdf

Tabs

playwright-cli tab-list
playwright-cli tab-new [url]
playwright-cli tab-close [index]
playwright-cli tab-select <index>

07 Who should try it

Playwright CLI is especially worth trying in these kinds of scenarios:

You are using Claude Code, Copilot, or another coding agent for E2E testing
You want a lighter browser automation interface without pushing large page structures into model context
You want one browser session to persist across multiple commands
You want to monitor agent-driven web tasks through a dashboard while they run

If your main question is how to make browser automation work efficiently with coding agents, Playwright CLI will likely feel more natural than traditional manual debugging workflows.

Playwright on KnightLi Blog

browser-harness, Playwright, and Puppeteer: which browser automation tool should you choose?

The relationship between Playwright and Puppeteer

Core differences

Browser support

Auto-waiting and stability

Multi-account workflows and context isolation

Tooling differences

Where browser-harness fits

Three-way comparison

Code feel

How to choose

Conclusion

What Is CloakBrowser? A More Realistic Browser for Playwright and Puppeteer

What Problem Does It Solve

Basic Usage

Browser Profile Manager

How It Differs From Regular Playwright

What To Watch Out For

Who It Is For

Summary

ai-goofish-monitor: An Open-Source AI Monitoring System for Goofish Listings

The Short Version

What Problem It Solves

Core Features

Workflow

Docker Deployment

Minimum Configuration

First Use

AI Tasks and Keyword Tasks

What the Web UI Does

Data Storage

Notification Channels

Developer Run

Who It Fits

Risks and Boundaries

Difference from Ordinary Scripts

How to Use It

Summary

Playwright CLI Video Recording: Recording, Chapter Markers, Overlays, and Debugging Tradeoffs

01 Basic Recording Flow

02 Best Practices

1. Use Descriptive Filenames

2. Record Entire Hero Scripts

03 Overlay API Summary

04 Tracing vs Video

05 Limitations

06 Quick Summary

References

Playwright CLI Session Management: Multiple Browser Sessions, Isolation, Persistence, and Cleanup

01 Named Browser Sessions

02 What Does Browser Session Isolation Separate?

03 Commands Related to Browser Sessions

04 Set a Default Session with an Environment Variable

05 Common Pattern: Concurrent Scraping

06 Common Pattern: A/B Test Sessions

07 Persisting Browser Profiles

08 The Default Browser Session

09 Session-Related Startup Configuration

10 Best Practices from the Official Docs

1. Use Meaningful Session Names

2. Clean Up Promptly After Use

3. Remove Stale Browser Data

11 Quick Summary

References

Playwright CLI storage state: Save Login Sessions, Read Cookies, and Local Storage

01 Save the current storage state

02 Load an existing storage state

03 View current cookies

04 Set cookies

05 Read localStorage

06 Write localStorage

07 Read sessionStorage

08 Write sessionStorage

09 View IndexedDB

10 A practical workflow

11 What to watch out for

12 Quick summary

References

Getting Started with Playwright CLI: Installation, Skills, Sessions, and Essential Commands

05 `--headed`, sessions, and the monitoring dashboard

`--headed`