agentbrowse - npm

npm

Search<br>Sign UpSign In

agentbrowse<br>0.3.3 • Public • Published 2 days ago<br>Readme<br>Code Beta<br>6 Dependencies<br>0 Dependents<br>11 Versions<br>agentbrowse

Drive any website from the terminal — built for AI coding agents.

Agents (Claude Code, Codex, …) are great at running CLIs and clumsy at clicking through web UIs. agentbrowse gives them a clean, parseable surface: open a page, read it as token-bounded markdown, follow links, fill and submit forms, and operate behind a login — all from terminal commands, with a persistent browser session that survives across invocations.

There is no separate web interface to wire up. The agent runs agentbrowse and gets structured output back.

Install

npm install -g agentbrowse<br># first run downloads the browser:<br>npx playwright install chromium

Quickstart

agentbrowse open https://example.com # navigate the session<br>agentbrowse read # current page as clean markdown<br>agentbrowse links # numbered, followable links<br>agentbrowse click "Learn more" # click by visible text...<br>agentbrowse click 2 # ...or by a number from links/find<br>agentbrowse read --json # structured output for machines<br>agentbrowse stop # end the session (frees the browser)

read/links accept an optional URL to open first, so agentbrowse read https://x.com is "open then read" in one step.

Make your agent use it by default

Install agentbrowse as a skill so your coding agent reaches for it automatically on web tasks — no prompting required:

npx agentbrowse skill # auto-detects Claude Code, Codex, Cursor, Gemini, Windsurf in this project<br>npx agentbrowse skill --global # or install once at the user level

It writes each agent's native format — a SKILL.md for Claude Code, a .cursor/rules rule for Cursor, an AGENTS.md block for Codex and others — and is safe to re-run (idempotent). Preview with --print; target one with npx agentbrowse skill claude|codex|cursor|gemini|windsurf.

Claude Code plugin — install the skill from this repo's built-in marketplace:

/plugin marketplace add mandarwagh9/agentbrowse-skill<br>/plugin install agentbrowse@agentbrowse

How it works

A background browser daemon (auto-spawned per session, local socket only) holds a live Playwright page, so state persists between separate commands — open, then later click, then read, all hit the same page. The daemon self-stops after inactivity.

Sessions are isolated by --session (default default), each with its own cookies and saved auth.

Commands

Command<br>What it does

open<br>Navigate the session to a URL

read [url]<br>Current page (or open first) as token-bounded markdown (--max-chars, --page)

links [url]<br>Numbered, followable links (--filter)

snapshot [url]

Accessibility-tree view : every actionable element with a stable [ref], role, name, state (--filter, --max, --json). The robust way to act

find<br>Locate elements by visible text (falls back to accessible name); numbers reusable by click

click<br>Click by a snapshot ref (robust), visible text, a links/find number, or a CSS selector

type<br>Type into a field (CSS selector or bare name)

fill -f name=value …<br>Fill form fields

submit [form]<br>Submit the current form

login<br>Open a real browser to authenticate once; persists the session for headless reuse

session save|load|clear<br>Manage saved auth/session state

stop<br>Stop the session's browser daemon

Add --json to any command for structured output. Errors go to stderr as { "error": { code, message } } with a non-zero exit code (2 usage, 3 navigation, 4 target-not-found, 5 daemon).

Authentication

agentbrowse login https://site/login opens a real browser window for you to log in (handling SSO, MFA, captchas an agent can't). On success it saves the session's cookies locally (~/.webcli/sessions//, gitignored); the agent then operates headlessly with that session. Credentials are typed into the browser by a human — never passed as CLI arguments.

Site manifests (optional)

Point agentbrowse at a site.agent.json to expose named, high-level commands for a specific site:

agentbrowse --site ./notion.agent.json search "roadmap"

A manifest declares pages, selectors, and commands as ordered steps with {pages.*} / {selectors.*} / {arg} / ${ENV} interpolation. Schema version: webcli-manifest-v0. See AGENTS.md for the agent-usage guide and the manifest format.

License

Free to use, including commercially — but not copyable. You may install, run,<br>and use agentbrowse; you may not copy, fork, redistribute, or modify it. See<br>LICENSE. (Versions 0.0.1–0.1.1 were released under MIT and keep that license.)

Readme<br>Keywords<br>none

Package Sidebar<br>Install<br>npm i agentbrowse

Repository<br>Gitgithub.com/mandarwagh9/agentbrowse

Homepage<br>github.com/mandarwagh9/agentbrowse#readme

DownloadsWeekly Downloads<br>1,555

Version<br>0.3.3

License<br>SEE LICENSE IN LICENSE

Last publish<br>2 days ago

Collaborators

mandarsagarwagh

Analyze security with SocketCheck bundle size View package health Explore dependencies<br>Report malware