Analysis updated 2026-05-18
Let an AI agent navigate and interact with web pages through terminal commands.
Automate clicking, filling forms, and taking screenshots from a script.
Run performance audits and Lighthouse checks from the command line.
Use Opera's built-in AI features like chat and research through CLI commands.
| operasoftware/opera-browser-cli | aliyun/openclaw-exporter-to-langfuse | anousss007/ng-blatui | |
|---|---|---|---|
| Stars | 11 | 11 | 11 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | moderate | moderate | moderate |
| Complexity | 3/5 | 4/5 | 3/5 |
| Audience | developer | ops devops | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires Node.js 20+ and the Opera browser installed, plus a one-time interactive setup wizard.
opera-browser-cli is a command-line tool that lets AI agents and developers control the Opera web browser through typed terminal commands. Instead of clicking around manually, you run short commands to navigate to websites, click buttons, fill in forms, take screenshots, and more. The tool works by sitting between your terminal and the Opera browser. When you type a command, it sends the instruction to a persistent bridge server running in the background, which talks to the browser's built-in developer tools using the DevTools Protocol. The bridge stays alive across commands so the browser does not restart with every invocation. A key design goal is being friendly to AI agents. Output uses TOON encoding, a compact format that cuts token usage roughly 40% compared to raw JSON. Every response also includes contextual next-step hints, so an AI can continue working without guessing what to do next. Beyond navigation, it supports clicking page elements by reference ID, typing into form fields, managing multiple browser tabs, running JavaScript, and capturing performance data including Lighthouse audits. It also exposes Opera's built-in AI through commands like chat, invoke-do, make, and research. The invoke-do and make commands require Opera Neon and let the AI carry out multi-step browsing tasks or generate a webpage on the fly. The tool is written in TypeScript and requires Node.js version 20 or higher, along with the Opera browser. You install it globally via npm and run a one-time setup wizard. It is a fork of chrome-devtools-axi and wraps opera-devtools-mcp with an AXI-compliant interface.
A command line tool that lets AI agents and developers drive the Opera browser with typed commands, built for token-efficient automation.
Mainly TypeScript. The stack also includes TypeScript, Node.js, DevTools Protocol.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.