ClawHub Integration

Browse Anything on ClawHub — AI Browser as a Skill for Every Agent

Your AI assistant should have a real browser. Install Browse Anything as a skill on ClawHub and unlock web automation inside Claude Code, Cursor, OpenClaw, Hermes, Codex, Gemini, Windsurf, or any other agent that speaks the skills protocol. One install, one API key, real Chromium on tap.

Install command
1

Install command

Compatible AI assistants
7+

Compatible AI assistants

Skill install — runs on your API key
Free

Skill install — runs on your API key

Chromium browser, no mocks
Real

Chromium browser, no mocks

Why your AI assistant needs a real browser

Modern AI coding assistants — Claude Code, Cursor, OpenClaw, Hermes, Codex, Gemini, Windsurf — are great at writing code, but they're blind to the web. When you ask Cursor to "scrape the YC company list" or Claude Code to "check what's new on Hacker News and summarize it", they either refuse, hallucinate the answer, or try to fetch raw HTML with a basic curl-style tool that fails on every modern JavaScript-rendered site.

Browse Anything fixes that gap by being a tool the assistant can call. The ClawHub skills protocol exposes Browse Anything as a typed capability your agent can invoke whenever it needs to interact with the web: navigate, click, type, scrape, screenshot, log in, fill forms — anything you'd do in a real browser, your AI assistant can now do too.

Crucially, this works in both directions. You can ask the assistant to use Browse Anything ("scrape that page for me"), or you can use Browse Anything's prompt language directly inside the assistant ("run this Browse Anything task and use the output to update my README"). The two layers compose naturally.

What ClawHub is and why it matters

ClawHub is the package manager for AI assistant skills — think 'npm for agent capabilities'. It standardizes how skills are discovered, installed, versioned, and invoked across a growing list of AI runtimes. The same skill installs identically into Claude Code, OpenClaw, Hermes, Cursor, and others, because each runtime implements the ClawHub skills protocol.

For you as a user, this means: install Browse Anything once on ClawHub, and it works everywhere. No per-IDE plugin to maintain. No three-way fork of the integration. Updates roll out via ClawHub the same way npm packages get new versions.

For Browse Anything specifically, the skill ships a curated set of high-leverage primitives — `browse`, `scrape`, `submit_form`, `screenshot`, `schedule_task`, `subscribe_to_changes` — that your assistant can compose freely. The skill is open and the manifest is public on ClawHub at https://clawhub.ai/mehdi149/browseanything.

Install in one command

Skill install through ClawHub is identical across runtimes — that's the whole point of standardization. Below are the exact commands for the most common assistants today.

  • OpenClaw CLIRun `openclaw skills install browseanything`. Then in any project, the skill is available to whichever agent you start with `openclaw`.
  • Claude CodeAdd Browse Anything to your `claude-skills.json` via `claude skills add browseanything` (or whatever Claude Code's current installer command is — check ClawHub docs). The skill autoloads on next session.
  • CursorOpen Cursor settings → MCP / Skills → add the ClawHub Browse Anything entry with your API key. The agent can now call Browse Anything from any chat or composer session.
  • HermesHermes consumes ClawHub skills natively. Install via the Hermes skill installer pointed at the ClawHub registry. Documented on the ClawHub page.
  • Codex / Gemini / Windsurf / othersAny agent that implements the ClawHub skills protocol — or supports MCP — can install Browse Anything. Browse Anything also publishes a native MCP server for runtimes that prefer MCP over ClawHub directly.

What the skill lets your assistant do

Once installed, the skill exposes typed primitives that the host agent picks up automatically. The agent decides when to call them based on user intent; you don't have to tell it explicitly to use Browse Anything.

  • browse(url, instructions)Navigate to a URL and follow plain-English instructions. Returns the final page state, extracted data, and a screenshot.
  • scrape(prompt)One-shot scraping. The agent describes the data it wants and the skill returns structured JSON.
  • submit_form(url, fields)Locate a form and submit it with the provided fields. Handles multi-step forms, dropdowns, file uploads, and consent banners.
  • screenshot(url)Headful Chromium screenshot. Useful when the assistant needs to 'see' the page to reason about it (great for design review or QA work).
  • schedule_task(prompt, schedule)Create a recurring task. The assistant can schedule reports, monitors, and pipelines without your hand-holding.
  • subscribe_to_changes(url, fields)Set up a change-monitoring task. The assistant can wire up alerting workflows in one call.

Workflows that become natural once your IDE has a browser

These are the workflows users report after installing Browse Anything in their AI assistant. None of them require leaving the IDE.

  • Read the docs the agent is implementing against"Read the Stripe webhook docs at /docs/webhooks and update my handler to support the new event types." The agent fetches the real page, reads it, edits your code accordingly.
  • QA the app you just shipped"Open the staging URL, sign in as the test user, run the signup flow, screenshot any error." The agent does the full QA pass and reports back inline.
  • Pull in production data the easy way"Log into Stripe and pull the count of subscriptions created last week, then update the dashboard query." Real data flows into your code review without context switching.
  • Set up monitoring as a one-liner"Schedule a daily 9am check of competitor.com/pricing and alert me on Slack if anything changes." Skip the UI, the agent creates the scheduled task for you.
  • Verify your changes affect the real web"Check whether my latest deploy is live at example.com — visit the page and confirm the new feature is rendered." Closes the feedback loop without leaving your editor.
  • Generate datasets on demand"I need a CSV of the top 200 ProductHunt launches from 2025 sorted by upvotes — go get it." The agent calls Browse Anything, returns the file, and you keep coding.

How API keys, billing, and credits work

The skill is free to install. Each Browse Anything action invoked through the skill is billed to the Browse Anything API key you configure — including the free tier. If you only call the skill occasionally for one-off scrapes, the free tier covers it. If you run scheduled jobs or high-volume scraping from inside your IDE, the Pro ($9.99/mo) or Ultra ($45/mo) plan applies.

The skill respects your plan's quotas. If you exceed credits, calls return a clear error the assistant can communicate to you ("Browse Anything credits exhausted, upgrade at platform.browseanything.io") rather than failing silently or hanging. There's no double-billing — the ClawHub layer is free.

Real prompts users run through the skill

These are prompts you'd give to your AI assistant (Claude Code, Cursor, OpenClaw, etc.) after installing Browse Anything via ClawHub. The assistant decides on its own to call the skill.

QA

Verify the staging deploy

Prompt

Use the browseanything skill to open https://staging.myapp.com, sign in with my test user, navigate to /dashboard, and confirm the new sidebar component renders. Send me the screenshot inline.

What you get back

Agent visits staging, signs in, navigates, screenshots, returns the image plus a short text confirmation. Replaces opening a browser yourself.

Code

Pull live data into a code review

Prompt

Before I merge this, use browseanything to check how many active users this feature has on production analytics dashboard. Update the PR description with the number.

What you get back

Assistant fetches the live number from your dashboard via the skill, edits the PR description. Honest data in code review without manual copy-paste.

Data

Generate a dataset for a new feature

Prompt

Use browseanything to scrape the top 100 GitHub repositories tagged 'agent' sorted by stars added this month. Save as data/agents.json in my project.

What you get back

JSON dataset added directly to your repo. The agent uses Browse Anything's scrape primitive, writes the file with normal file ops.

Docs

Read external docs and update code

Prompt

Use browseanything to read the official OpenAI Realtime API docs, then update my voice handler to match the latest spec. Cite the section you used.

What you get back

Agent reads live docs (no stale training data), edits your code with citations. The most underrated use of an IDE browser.

Schedule

Schedule a recurring task from inside the IDE

Prompt

Use browseanything to set up a daily 8am scheduled task that pulls top stories from Hacker News, summarizes them, and posts the summary to my Slack #morning channel.

What you get back

Agent calls schedule_task with the prompt. From this point on, the task runs daily without further intervention.

Forms

End-to-end form submission

Prompt

Use browseanything to submit a sample bug report on my support form at example.com/contact with: name='test', email='test@example.com', message='this is a smoke test of the contact form'. Confirm submission succeeded.

What you get back

Skill drives the form like a real user including any captchas. Returns success or detailed failure context for debugging.

See the official ClawHub listing

The skill is open and published at clawhub.ai/mehdi149/browseanything. Install instructions for each runtime, version history, and the full primitive list are on the ClawHub page.

openclaw skills install browseanything
# Then in any AI assistant:
# "Use the browseanything skill to ..."
Open the ClawHub listing

Frequently asked questions

Is the ClawHub skill free?

Yes. The skill itself is free to install. Each action consumed by the skill (browse, scrape, submit_form, etc.) uses credits from your Browse Anything account. The free Browse Anything tier covers light usage; Pro ($9.99/mo) or Ultra ($45/mo) cover heavier and scheduled workloads.

Which AI assistants are compatible?

Anything that implements the ClawHub skills protocol or MCP: Claude Code, Cursor, OpenClaw, Hermes, Codex, Gemini, Windsurf, and more arriving regularly. Browse Anything also publishes a standalone MCP server for runtimes that prefer MCP directly.

Where is my Browse Anything API key stored?

Locally, in your AI assistant's standard skills config (per the host runtime's conventions — e.g. macOS Keychain for Claude Code on Mac, encrypted secrets for OpenClaw). Browse Anything never sees or stores the key on the ClawHub side; calls flow directly from your agent to the Browse Anything API.

Can the assistant use Browse Anything without me asking each time?

Yes — that's the point. Once installed, the assistant treats Browse Anything as a normal tool. When it decides web access would help ("the user wants me to check what's on this page"), it calls the skill automatically. You can always ask it not to, or to ask first, with normal instruction.

What's the difference between ClawHub skill and using Browse Anything directly?

Using Browse Anything directly (web UI, API, Telegram) is best when you're already in a Browse Anything-first workflow. Using the ClawHub skill is best when your primary workflow is in another AI assistant (Claude Code, Cursor) and you want the assistant to invoke browser actions seamlessly. The two share the same backend and same credits.

Does the skill work for scheduled tasks?

Yes. The skill exposes a `schedule_task` primitive. Your assistant can create, list, and delete scheduled Browse Anything tasks the same way it creates files — from inside your normal workflow.

What's the latency like?

Browse and scrape primitives typically respond in 15-90 seconds depending on the task. Screenshot and form submit are usually 5-30 seconds. Schedule, subscribe, and listing primitives respond in under 2 seconds. The assistant handles the async wait natively without blocking your session.

Install the skill in 60 seconds

Free to install, free to try on the Browse Anything free tier. One command, every AI assistant. Give your agent a real browser.

Related use cases