Agent Browser

Community

itgoyo

agent-browser

Browser automation CLI for AI agents using agent-browser (Vercel Labs). Fast native Rust CLI with accessibility-tree based element selection. Use when you need headless browser control from the terminal — navigate, click, fill forms, screenshot, batch commands, AI chat mode.

Overview

Publisher	itgoyo
Repository	`hermes-skills`
Skill name	`agent-browser`
Stars	77
Forks	11
Bundled files	Instructions only
Links	Skill source Repository

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 itgoyo 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.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/itgoyo/hermes-skills/tree/main/autonomous-ai-agents/agent-browser
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.

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/itgoyo/hermes-skills.git /tmp/hermes-skills
mkdir -p .claude/skills
cp -r /tmp/hermes-skills/autonomous-ai-agents/agent-browser .claude/skills/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

Browser automation CLI for AI agents by Vercel Labs. Repo: https://github.com/vercel-labs/agent-browser

Installation

npm (recommended, already installed globally)


npm install -g agent-browser
agent-browser install   # download Chrome for Testing (first time only)

Homebrew (macOS)


brew install agent-browser
agent-browser install

Cargo (Rust)


cargo install agent-browser
agent-browser install

Update


agent-browser upgrade

Chrome is stored at: ~/.agent-browser/browsers/chrome-/

Quick Start

bash
agent-browser open example.com
agent-browser snapshot          # accessibility tree with @eN refs
agent-browser click @e2         # click element by ref
agent-browser fill @e3 "text"   # clear + fill input by ref
agent-browser screenshot page.png
agent-browser close

Core Commands

bash
agent-browser open <url>              # navigate (aliases: goto, navigate)
agent-browser snapshot                # accessibility tree with refs (best for AI)
agent-browser snapshot -i             # interactive snapshot (live)
agent-browser click <sel>             # click element
agent-browser fill <sel> <text>       # clear and fill
agent-browser type <sel> <text>       # type into element
agent-browser press <key>             # press key (Enter, Tab, Control+a)
agent-browser scroll <dir> [px]       # scroll up/down/left/right
agent-browser screenshot [path]       # screenshot (--full for full page)
agent-browser screenshot --annotate   # annotated with numbered labels
agent-browser eval <js>               # run JavaScript
agent-browser wait <selector>         # wait for element
agent-browser wait --text "text"      # wait for text
agent-browser wait <ms>               # wait milliseconds
agent-browser close                   # close browser

Get Info

bash
agent-browser get text <sel>
agent-browser get html <sel>
agent-browser get value <sel>
agent-browser get title
agent-browser get url

Semantic Locators (find)

bash
agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "test@test.com"
agent-browser find nth 2 "a" text

Batch Execution

bash
# argument mode
agent-browser batch "open https://example.com" "snapshot -i" "screenshot"

# stdin JSON mode
echo '[["open","https://example.com"],["snapshot"],["screenshot","out.png"]]' | agent-browser batch --json

AI Chat Mode

bash
agent-browser chat "Go to example.com and take a screenshot"  # single-shot
agent-browser chat                                              # interactive REPL

Notes & Pitfalls

Always run agent-browser install once after install to download Chrome.
Chrome stored at ~/.agent-browser/browsers/
Selectors: prefer @eN refs from snapshot for AI use; CSS selectors also work.
On Linux: agent-browser install --with-deps to install system dependencies.
Requires network proxy on restricted networks (set https_proxy before install).

Frequently asked questions

What does the Agent Browser AI skill do?

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/itgoyo/hermes-skills/tree/main/autonomous-ai-agents/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 itgoyo. 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.

View all

Claw Score

openclaw

OrganizationPopular

Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.

Clawsweeper

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions…

Control Ui E2e

Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright end-to-end checks, mocked Gateway flows,…

Deslop

Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

agent-browser

Installation

npm (recommended, already installed globally)

Homebrew (macOS)

Cargo (Rust)

Update

Quick Start

Core Commands

Get Info

Semantic Locators (find)

Batch Execution

AI Chat Mode

Notes & Pitfalls

Frequently asked questions

Related AI Skills

Set up your own AI workspace now