Browser Automation

Three families of nodes touch the web, and they solve different problems. Web search (see Web Search) finds pages and returns snippets. Scraping (see Scraping & Proxies) fetches and extracts content from pages you already know. Browser automation — this page — drives an actual browser session so a workflow or agent can navigate, click, type, and read pages that require real interaction. Two nodes live here:

Node	Engine	Maturity
Browser	`agent-browser` CLI with a bundled Chrome-for-Testing (or your system browser)	Stable
Browser Harness	Your real Chrome over raw CDP (`browser-use/browser-harness`)	Alpha / experimental

Default to Browser. Reach for Browser Harness when the task needs your real Chrome profile and logins, bot-hostile or shadow-DOM-heavy sites, iframes, or raw CDP access.

Browser

Interactive browser automation via the agent-browser CLI. Also usable as an AI agent tool (tool name browser). First-use install is automatic. The node installs agent-browser from npm into OpenCompany’s shared package tree on first use (npm must be on PATH), then fetches the Chrome-for-Testing runtime — a roughly 150 MB Chromium download — so expect the very first run to take a while.

Operations

14 discrete operations plus a batch meta-operation:

Operation	What it does
`navigate`	Open a URL (requires URL)
`click`	Click an element (requires Selector)
`type`	Type text keystroke-by-keystroke into an element
`fill`	Set an input’s value directly
`screenshot`	Capture the page (optional full-page, annotation, png/jpeg)
`snapshot`	Accessibility-tree snapshot with stable `@eN` element refs
`get_text` / `get_html`	Extract text or HTML from an element
`eval`	Evaluate a JavaScript expression (requires Expression)
`wait`	Wait for a selector to appear
`scroll`	Scroll in a direction by an amount
`select`	Choose a dropdown option
`console` / `errors`	Read the page’s console output / errors
`batch`	Run a JSON array of commands in one call

Operations that act on an element — click, type, fill, get_text, get_html, wait, select — require Selector (a CSS selector or an @eN ref from a snapshot). The recommended agent loop is navigate -> snapshot -> click/fill using the @eN refs the snapshot returned -> snapshot again to verify.

Key parameters

select

default:"navigate"

One of the operations above

string

Target URL (required for navigate)

string

CSS selector or @eN ref from a snapshot (required for element operations)

string

Session id. Leave empty to use a per-run session — cookies, open tabs, and auth persist across sequential operations that share the same session, and every browser call in one workflow/agent run (including delegated sub-agents) reuses one browser instance.

select

default:"chrome"

chrome, edge, chromium, bundled_explicit (the bundled Chrome-for-Testing), or custom (set Executable Path)

boolean

default:"true"

Show the browser window; disable for headless runs

number

default:"30"

Per-action timeout in seconds (1-600)

Additional knobs: full_page / annotate / screenshot_format / screenshot_quality (screenshots), direction / amount (scroll), commands (batch JSON), auto_connect (reuse an already-running CDP browser), chrome_profile, user_agent, proxy, action_delay, executable_path, new_window.

Output

{
  "operation": "get_text",
  "data": "...the CLI's result for the operation...",
  "session": "opencompany_a1b2c3d4"
}

data is whatever agent-browser returned for the operation (parsed JSON when available, raw text otherwise). Responses larger than 100 KB are truncated.

Sessions and limits

Concurrent browser instances are capped by BROWSER_MAX_INSTANCES (default 3); when the cap would be exceeded, the oldest session is closed first.
Idle browsers shut themselves down after BROWSER_IDLE_TIMEOUT_MS (default 600000 ms; 0 disables).

Browser Harness

Browser Harness is alpha and experimental. It wraps the upstream browser-use/browser-harness project (v0.1.x) and executes agent-authored Python with your real, logged-in Chrome attached. Treat it as a power tool: it is visible in dev mode only, and its operations are marked destructive. Default to the stable Browser node.

Browser Harness drives your real Chrome over the Chrome DevTools Protocol (CDP) — no Playwright, no bundled Chromium. That means it sees your actual profile, cookies, and logins, which is exactly why it exists: sites that defeat headless automation or need your session state. It is a sibling of the Browser node, not a replacement:

	Browser (agent-browser)	Browser Harness
Engine	npm CLI + bundled Chrome-for-Testing (or system browser)	Your real Chrome over raw CDP
Interaction	Accessibility tree, `@eN` refs	Screenshots + coordinate clicks + `js()`
Sessions	Named sessions, instance cap, idle timeout	One shared browser
Agent surface	Structured operations	Freeform Python against helpers
Maturity	Stable	Alpha (v0.1.x)

Chrome must be started with remote debugging

The harness needs a CDP-reachable Chrome. It discovers one in this order:

A BU_CDP_URL (or BU_CDP_WS) environment variable pointing at a dedicated automation Chrome.
The DevToolsActivePort file Chrome writes when you enable chrome://inspect/#remote-debugging (“Allow remote debugging for this browser instance”).
A port probe on 9222/9223 — e.g. Chrome launched with --remote-debugging-port=9222.

If calls fail with connection guidance, run the doctor operation first — it returns the full connection checklist.

Operations

select

default:"run_python"

run_python (primary), goto, screenshot, js, tabs, or doctor

code

Python for run_python. Roughly 25 helpers are pre-imported (goto_url, click_at_xy, capture_screenshot, js, fill_input, wait_for_load, …). Print a JSON object as the final line for structured output.

string

URL to open (for goto)

string

JavaScript to evaluate in the page (for js)

boolean

default:"false"

Capture the full scrollable page (for screenshot)

number

default:"60"

Script timeout in seconds (5-600)

The driving model is “the LLM writes Python”: agents follow a see-act-verify loop of capture_screenshot() to see the page, click_at_xy(x, y) to interact, wait_for_load(), then js(...) for DOM reads.

Output

{
  "operation": "run_python",
  "data": "…whatever the script printed…"
}

Install

Install is lazy: first use runs uv tool install --python 3.12 browser-harness, so uv must be on PATH. If the node reports that browser-harness could not be installed, install uv and retry — it installs automatically on the next use.

Example: check a page and summarize

Fetch a live page in a real browser, extract the visible text, and have an agent summarize it:

[Cron Scheduler] --> [Browser (navigate)] --> [Browser (get_text)] --> [AI Agent] --> [Console]

Browser #1 — Operation: navigate, URL: https://news.ycombinator.com.
Browser #2 — Operation: get_text, Selector: body. Leave Session empty on both nodes; they share the per-run session automatically, so the second node reads the page the first one opened.
AI Agent — prompt it to summarize the extracted text.

Alternatively, connect a single Browser node to the agent’s tools input and let the agent drive the navigate/snapshot/click loop itself.

Tips

Prefer snapshot + @eN refs over hand-written CSS selectors when an agent drives the browser — the refs are stable within a page state and survive minor DOM differences.

Leave Session empty in agent workflows. Every call in the same run reuses one browser automatically, while separate runs stay isolated.

The very first Browser run downloads the Chrome-for-Testing runtime (~150 MB). Later runs start fast.

Scraping & Proxies

Fetch and extract known pages without a full browser

Web Search

Find pages before you open them

AI Agents

Let an agent drive the browser as a tool

Code Executors

Post-process extracted content

Concepts

Node catalog

Browser

Operations

Key parameters

Output

Sessions and limits

Browser Harness

Chrome must be started with remote debugging

Operations

Output

Install

Example: check a page and summarize

Tips

Scraping & Proxies

Web Search

AI Agents

Code Executors

​Browser

​Operations

​Key parameters

​Output

​Sessions and limits

​Browser Harness

​Chrome must be started with remote debugging

​Operations

​Output

​Install

​Example: check a page and summarize

​Tips

​Related

Scraping & Proxies

Web Search

AI Agents

Code Executors

Browser

Operations

Key parameters

Output

Sessions and limits

Browser Harness

Chrome must be started with remote debugging

Operations

Output

Install

Example: check a page and summarize

Tips

Related