Agent Browser — Browser Automation CLI for AI Agents
Fast browser automation CLI for AI agents — navigate pages, click, fill forms, screenshot and scrape via Chrome/Chromium CDP
- What
- Fast browser automation CLI for AI agents — navigate pages, click, fill forms, screenshot and scrape via Chrome/Chromium CDP
- Cost
- Free
- Needs
- Node.js/npm and a terminal where you can install global packages. No account or API key.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a fast browser-automation CLI built for AI agents: it drives Chrome/Chromium over CDP with accessibility-tree snapshots and compact element refs, so an agent can navigate pages, click buttons, fill forms, take screenshots, extract data, test web apps, or automate Electron desktop apps (VS Code, Slack, Discord, Figma) and Slack workspaces. Ships as a native Rust binary (no Playwright/Puppeteer dependency), with sessions, an authentication vault, state persistence and video recording; specialized skill packs load on demand (`electron`, `slack`, `dogfood` for exploratory QA, `vercel-sandbox`, `agentcore`). Discovered via skills.sh, listed here with credit to its creator by @vercel-labs. Honest caveats: this is a developer CLI, not an in-chat skill — install via `npm i -g agent-browser`, then `agent-browser install` for the browser; the SKILL.md in the repo is a discovery stub, the real usage content is served by the CLI itself (`agent-browser skills get core`) and always matches the installed version; most useful through an agent with computer access (like Muse) that can run the CLI for you. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Version:
Install
Prerequisites: Node.js/npm and a terminal where you can install global packages. No account or API key. Install "Agent Browser" for me. A fast browser-automation CLI for AI agents: drives Chrome/Chromium over CDP — navigate pages, click, fill forms, screenshot, scrape data, test web apps, automate Electron apps and Slack. Repository: https://github.com/vercel-labs/agent-browser 1. Install the CLI globally: `npm i -g agent-browser`, then run `agent-browser install` to set up the browser. Summarize what it does in one or two sentences. 2. Safety check: this is a well-known Vercel Labs open-source project (Apache-2.0). Review the repo briefly for anything suspicious. This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Load the real usage content from the CLI itself: run `agent-browser skills get core` and summarize the available workflows. 4. Verify: `agent-browser --version` runs and the browser launches. 5. Report what was installed, where, and what I still need to do myself (e.g. tell you which site to automate first). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the install. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.