Short answer: install agent-browser, point its documented custom executable setting at the Edge binary on your computer, and verify the result with a simple open-and-snapshot workflow. The project’s standard installer downloads Chrome for Testing, not Edge. Its documentation supports a custom executable path, but the official material does not provide a complete, Edge-specific recipe or compatibility matrix. Treat Edge use as an environment-specific configuration to validate on your operating system, Edge channel, and installed agent-browser version.
What agent-browser does with Edge
agent-browser is a command-line browser automation tool. Its normal installation path installs the package globally and then downloads Chrome for Testing. Microsoft Edge is a Chromium-based browser, but that fact alone is not proof that every Edge release, platform, or automation feature works with agent-browser.
The project documents a custom browser executable option. You can supply the path with the --executable-path command-line flag or the AGENT_BROWSER_EXECUTABLE_PATH environment variable. Persistent configuration also has an executablePath setting. Those are the supported mechanisms to try; the documentation examples use Chromium and Chrome rather than an Edge-specific walkthrough.
Install agent-browser
Global installation
- Install a current Node.js release suitable for your project.
- Install the CLI:
npm install -g agent-browser. - Run the browser setup command:
agent-browser install.
The final command downloads Chrome for Testing by default. On Linux, add operating-system dependencies when required: agent-browser install --with-deps.
#1 Best Overall
- Microsoft Surface Laptop Go 2 | Certified Refurbished, Amazon Renewed | 12.4-inch (1536 x 1024) LCD Touchscreen Display | Windows 11 Professional | Platinum Silver Color
- This Certified Refurbished product is tested and certified to look and work like new. The refurbishing process includes functionality testing, basic cleaning, inspection, and repackaging. The product ships with all relevant accessories, a minimum 90-day warranty, and may arrive in a generic box.
- 256GB Solid State Drive, 16GB RAM, Intel Core i5-1135G7 CPU, Convenient security with Windows Hello sign-in, plus Fingerprint Power Button with Windows Hello and One Touch sign-in on select models., Integrated Intel UHD Graphics
- Bluetooth, Wi-Fi: 802.11ax Wireless LAN, Run your favorite apps and keep up on social media with a 11th Gen Intel Core Processor.
Other documented installation routes
The project also documents npx, a project-local npm install, Homebrew, Cargo, and installation from source. Choose one route and keep the resulting CLI and configuration in the same environment; mixing a global binary with a different project-local version makes troubleshooting harder.
Find the Edge executable
You need the actual executable path for the Edge installation you intend to automate. Microsoft’s Edge DevTools MCP documentation lists default locations for Edge Stable, Beta, and Dev channels on Windows, macOS, and Linux. That page documents paths for chrome-devtools-mcp, a separate tool, so use those locations only as references for locating Edge—not as proof that agent-browser has certified support for that combination.
Common path patterns
- Windows: Edge is commonly installed below
Program Filesor a per-userAppDatadirectory, depending on channel and installation scope. - macOS: the application bundle is normally under
/Applications(or a user’s Applications folder); the executable is inside the bundle’sContents/MacOSdirectory. - Linux: package-managed installations commonly expose an executable such as
microsoft-edgeormicrosoft-edge-stableon thePATH.
Do not copy a path from another machine. Confirm that the file exists, is executable, and belongs to the Edge channel you want.
Launch agent-browser with Edge
One-off command-line selection
Pass the executable path on the command that starts your browser session. Quote paths containing spaces.
agent-browser --executable-path "C:Program Files (x86)MicrosoftEdgeApplicationmsedge.exe" open https://example.comOn macOS, a typical bundle path would look like:
agent-browser --executable-path "/Applications/Microsoft Edge.app/Contents/MacOS/Microsoft Edge" open https://example.comOn Linux, use the binary found on your system:
agent-browser --executable-path /usr/bin/microsoft-edge-stable open https://example.comThese commands demonstrate the documented custom-executable mechanism. They are not an official guarantee that a particular Edge channel will launch successfully.
Rank #2
- Microsoft Surface Laptop Go | Certified Refurbished, Amazon Renewed | 12.4-inch (1536 x 1024) LCD Touchscreen Display | Windows 10 Professional
- This Certified Refurbished product is tested and certified to look and work like new. The refurbishing process includes functionality testing, basic cleaning, inspection, and repackaging. The product ships with all relevant accessories, a minimum 90-day warranty, and may arrive in a generic box.
- 256GB Solid State Drive, 16GB RAM, Intel Core i5-1035G1 CPU, Convenient security with Windows Hello sign-in, plus Fingerprint Power Button with Windows Hello and One Touch sign-in on select models., Integrated Intel UHD Graphics
- Bluetooth, Wi-Fi: 802.11ac Wireless LAN, Run your favorite apps and keep up on social media with a 10th Gen Intel Core Processor.
Environment-variable selection
Set AGENT_BROWSER_EXECUTABLE_PATH before running the CLI when you want the choice to apply to multiple commands.
# macOS or Linux
export AGENT_BROWSER_EXECUTABLE_PATH="/usr/bin/microsoft-edge-stable"
agent-browser open https://example.com
# Windows PowerShell
$env:AGENT_BROWSER_EXECUTABLE_PATH = "C:Program Files (x86)MicrosoftEdgeApplicationmsedge.exe"
agent-browser open https://example.comPersistent configuration
The configuration documentation names an executablePath setting for persistent use. Put the path in the user or project configuration supported by your installed version, then run the CLI without the flag. Configuration precedence is documented as:
- User configuration
- Project configuration
- Environment variables
- CLI flags
Higher-priority values override lower-priority values. Consequently, a command-line path can temporarily override a stale project setting, while an environment variable can override both configuration files.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Verify the browser before automating a real task
Use a small, observable test before building a production workflow. The standard agent-browser interaction pattern is open, inspect an accessibility snapshot, act on an element reference, and take a fresh snapshot after the page changes.
- Open a stable page:
agent-browser --executable-path "/path/to/edge" open https://example.com- Request the accessibility snapshot:
agent-browser snapshotInspect the returned roles, names, and element references. A page title, heading, or link confirms that the session reached the page.
Rank #3
- [This is a Copilot+ PC] — A new AI era begins. Experience enhanced performance and AI capabilities with Copilot+ PC, boosting productivity with security and privacy in mind
- [Introducing Surface Laptop] — Power, speed, and touchscreen versatility with AI features. Transform your work, play, and creativity with a razor-thin display and best-in-class specs.
- [Exceptional Performance] — Surface Laptop delivers faster performance than the MacBook Air M3[1], with blazing NPU speed for seamless productivity and AI apps.
- [All-Day Battery Life] — Up to 20 hours of battery life[6] to focus, create, and play all day.
- [Brilliant 15” Touchscreen Display] — Bright HDR tech, ultra-thin design, and optimized screen space.
- Interact with a reference from that snapshot. For example, if the snapshot labels a link
@e1, use the action syntax documented by your installed version to click or otherwise act on that reference. - Request another snapshot after navigation, a click, or any DOM-changing operation:
agent-browser snapshotReferences can change when the page changes, so do not assume an old reference remains valid. Confirm that Edge—not the bundled Chrome—was launched in your target environment before relying on browser-specific behavior.
Edge-specific choices and trade-offs
Use bundled Chrome for Testing
This is the path the default installer is designed around. It is usually the least ambiguous option because the browser download and the tool’s documented examples are aligned.
Recommended Free Tools
Use a locally installed Edge executable
This lets you test the browser your users or organization actually run, including a particular Edge channel. It also introduces variables that the reviewed documentation does not settle: operating-system packaging, Edge version, profile policies, sandboxing, and protocol behavior. Pin and record the exact Edge and agent-browser versions when reproducing a result.
Connect to an existing browser
agent-browser documentation also describes connecting through Chrome’s DevTools Protocol (CDP), with Chrome-oriented examples. An existing Edge session may expose a compatible endpoint, but Edge-specific CDP success is not established by those examples. Treat this as an experiment, keep the browser and tool versions aligned, and avoid using a personal profile for unattended automation.
Common errors and fixes
“Executable not found” or an immediate launch failure
- Check the path character-for-character and verify the file exists.
- On macOS, point to the executable inside the application bundle, not only to the
.appdirectory. - On Linux, confirm permissions and whether the binary is actually named
microsoft-edgeormicrosoft-edge-stable. - Quote Windows and macOS paths containing spaces.
Chrome still opens
- Print or inspect
AGENT_BROWSER_EXECUTABLE_PATHin the same shell that runs agent-browser. - Look for a project configuration overriding your user configuration.
- Use
--executable-pathfor a one-off test; its documented precedence is higher than environment and file-based settings. - Check that the command is invoking the agent-browser version you think it is, rather than a different global or project-local installation.
Edge opens and then exits
Try a clean, non-personal profile and a simple public URL. Corporate policy, profile locks, sandbox restrictions, incompatible flags, or an unsupported Edge/tool combination can all terminate a session. Compare the result with the bundled Chrome for Testing installation; if Chrome works and Edge does not, record the exact versions and platform before reporting the issue.
Rank #4
- With 16 GB of memory, runs as many programs as you want without losing the execution
- The 13.5" 2256 x 1504 screen provides a great movie watching experience
- 512 GB SSD is enough to store your essential documents and files, favorite songs, movies and pictures
- 8 Hours battery run time helps you stay unwired and work longer non-stop
The page loads but references or actions fail
- Take a new snapshot after every navigation or DOM-changing action.
- Wait for the page state your workflow needs before reading the snapshot.
- Use accessible names and roles rather than brittle coordinates.
- Test pages without login walls, bot checks, or transient popups while isolating the browser-launch problem.
Linux reports missing libraries
Run agent-browser install --with-deps where supported, or install the dependencies required by your distribution. A successful npm installation does not guarantee that a Linux host has every graphical or sandbox library needed to start Edge.
Free tools Windows power users keep installed
One-click scans. No signup required.
Reliability checklist for production use
- Pin the agent-browser version and document the Edge channel and version.
- Use a dedicated automation profile; do not expose personal cookies or saved passwords.
- Keep the executable path in deployment configuration rather than hard-coding a developer’s home directory.
- Run a startup smoke test that opens a known URL and captures a snapshot.
- Log the selected executable, operating system, browser version, and failure output.
- Retest after Edge updates, agent-browser upgrades, or policy changes.
Default browser versus automation browser
Making Edge the operating system’s default browser changes file and URL associations. It does not tell agent-browser which executable to launch. Automation selection comes from the custom executable flag, environment variable, or agent-browser configuration. You may therefore use Edge for automation while another browser remains the OS default, or make Edge the default without changing an existing agent-browser setup.
Or skip the browser setup
If your goal is simply to obtain a clean website image or PDF rather than drive an interactive Edge session, ScreenshotNeo provides a website screenshot API and MCP server. One GET request returns PNG, JPEG, WebP, or PDF; it handles the browser environment for you.
cURL
curl -G "https://api.screenshotneo.com/v1/shot" -d access_key=YOUR_API_KEY --data-urlencode url=https://stripe.com -o shot.webpPython
import requests
r = requests.get("https://api.screenshotneo.com/v1/shot", params={"access_key": "YOUR_API_KEY", "url": "https://stripe.com"}, timeout=90)
open("shot.webp", "wb").write(r.content)Node.js
const q = new URLSearchParams({ access_key: 'YOUR_API_KEY', url: 'https://stripe.com' });
const res = await fetch(`https://api.screenshotneo.com/v1/shot?${q}`);Before capture, ScreenshotNeo accepts cookie or consent banners and removes more than 60 known consent platforms, newsletter popups, and chat widgets; each step can be disabled. Bot checks or CAPTCHAs, blank pages, timeouts, failed loads, and cache hits are not billed, and response headers identify the page verdict and billing result. Its MCP server includes take_screenshot, get_page_info, and capture_pdf for Claude, Cursor, and other MCP clients. Every feature is included on every plan; 1,000 screenshots per month are free without a card, and paid plans start at $5 for 3,000 shots. See the ScreenshotNeo documentation for options and authentication, then sign up free.
Frequently Asked Questions
Does agent-browser officially support Microsoft Edge?
The documented interface supports a custom executable path, but the official material reviewed does not publish an Edge-specific setup or compatibility matrix. Validate your exact platform, Edge channel, and agent-browser version locally.
Do these 3 things before closing this tab:
1Scan for outdated or missing drivers - takes under a minute2Clear out junk files and repair common Windows errors3Fix the driver behind crashes, sound loss and screen glitchesCan I use my normal Edge profile?
Use a separate automation profile instead. A personal profile can contain cookies, passwords, extensions, and policy settings that create security and reproducibility problems.
Why does changing the Windows default browser not affect agent-browser?
The operating-system default controls URL and file associations. agent-browser chooses its executable through its flag, environment variable, or configuration settings.
What should I test first after configuring Edge?
Open a stable public page, request an accessibility snapshot, perform one simple action, and request a second snapshot. This verifies launch, navigation, references, and post-action state before you automate a larger workflow.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
