Agent Browser logo

Agent Browser

CommunityPopular
am-will
Agent Browser

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

Overview

Publisheram-will
Repositorycodex-skills
Skill nameAgent Browser
Stars
1K
Forks
60
Bundled files
Instructions only
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by am-will on GitHub. Read the source before you install it.

Installation

Install the Agent Browser AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/am-will/codex-skills.git /tmp/codex-skills
mkdir -p .claude/skills
cp -r /tmp/codex-skills/skills/agent-browser .claude/skills/am-will-agent-browser
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agent Browser in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Agent Browser on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Agent Browser is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Agent Browser

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

Installation

npm recommended

bash
npm install -g agent-browser
agent-browser install
agent-browser install --with-deps

From Source

bash
git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
agent-browser install

Quick Start

bash
agent-browser open example.com
agent-browser snapshot
agent-browser click @e2
agent-browser fill @e3 "test@example.com"
agent-browser get text @e1
agent-browser screenshot page.png
agent-browser close

Using Real Chrome Profile (for OAuth/Logged-in Sessions)

For sites requiring Google/Discord/etc login (like star-swap.com):

Method 1: Launch Chrome with custom profile, connect via CDP

bash
# Terminal 1: Launch Chrome with your real profile and remote debugging
google-chrome --remote-debugging-port=9222 --user-data-dir=/home/willr/.config/google-chrome/Default &

# Terminal 2: Connect agent-browser to that Chrome instance
agent-browser --cdp 9222 open "https://star-swap.com"
agent-browser --cdp 9222 snapshot -i
agent-browser --cdp 9222 click e2

# This reuses your existing Google session - no re-login needed!
# Works for: Google OAuth, Discord OAuth, any site you're logged into in Chrome

Method 2: Session persistence (first-time manual login)

bash
# First time: headed mode, login manually
agent-browser --headed --session starswap open "https://star-swap.com"
# Complete Google OAuth manually in the browser window
# Close when done

# Future runs: cookies persist!
agent-browser --session starswap open "https://star-swap.com"
# Already logged in automatically

am.will.ryan Chrome profile: /home/willr/.config/google-chrome/Default

Core Commands

Navigation

bash
agent-browser open <url>
agent-browser back
agent-browser forward
agent-browser reload

Interaction

bash
agent-browser click <sel>
agent-browser dblclick <sel>
agent-browser focus <sel>
agent-browser type <sel> <text>
agent-browser fill <sel> <text>
agent-browser clear <sel>
agent-browser press <key>
agent-browser keydown <key>
agent-browser keyup <key>
agent-browser hover <sel>
agent-browser select <sel> <val>
agent-browser check <sel>
agent-browser uncheck <sel>
agent-browser drag <src> <tgt>
agent-browser upload <sel> <files>

Extraction and Info

bash
agent-browser snapshot
agent-browser get text <sel>
agent-browser get html <sel>
agent-browser get value <sel>
agent-browser get attr <sel> <attr>
agent-browser get title
agent-browser get url
agent-browser get count <sel>
agent-browser get box <sel>
agent-browser screenshot [path]
agent-browser pdf <path>

Check State

bash
agent-browser is visible <sel>
agent-browser is enabled <sel>
agent-browser is checked <sel>

Find Elements

  • agent-browser find role [value]
  • agent-browser find text
  • agent-browser find label [value]
  • agent-browser find placeholder [value]
  • agent-browser find alt
  • agent-browser find title
  • agent-browser find testid [value]

Actions include click, fill, check, hover, and text.

Wait and Timing

bash
agent-browser wait <selector>
agent-browser wait <ms>
agent-browser wait --text "Welcome"
agent-browser wait --url "**/dash"
agent-browser wait --load networkidle

Advanced Control

bash
agent-browser scroll <dir> [px]
agent-browser scrollintoview <sel>
agent-browser eval <js>
agent-browser mouse move <x> <y>
agent-browser cookies
agent-browser storage local
agent-browser tab new [url]
agent-browser frame <sel>
agent-browser dialog accept [text]

Sessions

Run multiple isolated browser instances.

bash
agent-browser --session agent1 open site-a.com
agent-browser --session agent2 open site-b.com

Snapshot Options

The snapshot command supports filtering to reduce output size.

  • agent-browser snapshot -i
  • agent-browser snapshot -c
  • agent-browser snapshot -d 3
  • agent-browser snapshot -s "#main"

Selectors and Refs

Refs provide deterministic element selection from snapshots. Use the @ref syntax.

bash
agent-browser snapshot
agent-browser click @e2

Agent Mode

Use --json for machine readable output.

bash
agent-browser snapshot --json

Optimal AI Workflow

  • Navigate with agent-browser open
  • Observe with agent-browser snapshot -i --json
  • Act with @ref from the snapshot
  • Verify with agent-browser snapshot

Troubleshooting

  • If the command is not found on Linux ARM64, use the full path in the bin folder.
  • If an element is not found, use snapshot to find the correct ref.
  • If the page is not loaded, add a wait command after navigation.
  • Use --headed to see the browser window for debugging.

Options

  • --session uses an isolated session.
  • --json provides JSON output.
  • --full takes a full page screenshot.
  • --headed shows the browser window.
  • --timeout sets the command timeout in milliseconds.

Notes

  • Refs are stable per page load but change on navigation.
  • Always snapshot after navigation to get new refs.
  • Use fill instead of type for input fields to ensure existing text is cleared.

Frequently asked questions

What does the Agent Browser AI skill do?

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

Why use Agent Browser on TypingMind?

Because you install it once and use it with any model. Agent Browser is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Agent Browser in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/am-will/codex-skills/tree/main/skills/agent-browser. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Agent Browser?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Agent Browser?

As many as you like. As long as a model supports skills, you can use Agent Browser with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Agent Browser AI skill free?

It is published on GitHub by am-will. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
mattpocock logo

Prototype

mattpocock
CommunityPopular

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

22.3K
264.4K
3 files
View
mattpocock logo

Research

mattpocock
CommunityPopular

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading…

22.3K
264.4K
1 files
View
mattpocock logo

Resolving Merge Conflicts

mattpocock
CommunityPopular

Use when you need to resolve an in-progress git merge/rebase conflict.

22.3K
264.4K
1 files
View
mattpocock logo

Setup Matt Pocock Skills

mattpocock
CommunityPopular

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

22.3K
264.4K
6 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇