OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Browser Agents

Moli

Moli is a Rust-based headless browser runtime that lets AI agents and automation clients fetch and extract web pages, search the web, and automate browser tasks through a CLI, CDP, WebDriver Classic or WebDriver BiDi.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Moli — OpenViST project profile in Browser Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Moli when an agent or automation workflow needs a headless browser to retrieve page structure, interact with a page, or produce visual exports. Use the CLI for individual fetches and the server with a browser-control client for protocol-based automation.

Who it is for

  • AI-agent developers who need a browser runtime for web research or page extraction.
  • Automation engineers who want to connect browser clients through CDP or WebDriver.
  • CLI users who need page content or visual exports from a URL.

Documented uses

  • Fetch a page and export its content as Markdown or a semantic tree.
  • Search the web and provide page content to an agent workflow.
  • Automate browser tasks through the CLI or browser-control protocols.
  • Generate screenshots or paginated PDFs when visual output is needed.
Before you choose

Requirements & limits

The project is open source under the Apache-2.0 license and documents support for Linux, macOS and Windows.

  • The CLI can return Markdown or a semantic tree, while screenshots, full-page images and PDFs require layout output.
  • The server exposes CDP, WebDriver Classic and WebDriver BiDi; the documented Playwright example connects over CDP.
  • Moli is written in Rust and can be used as a CLI or started as a browser automation server.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Fetch a page as Markdown

Use Moli's CLI to load a URL and export its page content as Markdown.

Before you start

  • Moli installed and available as the moli command.
  • A page URL to fetch.

Steps

  1. Run moli fetch --dump markdown --wait-until done https://example.com, replacing the example URL with the target.

  2. Read the Markdown output produced by the command.

Expected outcome

A Markdown representation of the fetched page.

Guide limitations

  • The documented command uses --wait-until done; other waiting and output options are separate CLI settings.
  • This fetch recipe does not perform page interactions.
Documentation 1 ↗
Source-based practical guide

Expose Moli through CDP for Playwright

Start Moli's automation server and connect a Playwright client over CDP.

Before you start

  • Moli installed.
  • Playwright available to the client project.

Steps

  1. Start the browser server with moli serve.

  2. Connect Playwright to http://127.0.0.1:9222 using chromium.connectOverCDP.

  3. Use the connected page to navigate to a URL and read its body text, following the documented example.

Expected outcome

A Playwright client connected to Moli through CDP and able to navigate to a page and read text.

Guide limitations

  • The example is specifically a CDP connection; it does not demonstrate a particular AI-agent integration.
  • The documented server command is the basic DOM-first configuration; layout and additional resource options require separate flags.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
lexmount/moli · Official homepage title · retained in its source language
How we review sourcesSuggest a correction