Moli
by Lexmount
Fetches, extracts, and automates web pages in an open-source Rust headless browser that outputs Markdown or semantic trees and serves CDP and WebDriver, for agents reading the web.
Skills
Page Extraction
Renders a page as HTML, Markdown, JSON, or a compact semantic tree with moli fetch.
Screenshots and PDF
Writes viewport or full-page PNGs and paginated PDFs when on-demand layout is enabled.
Scripted Interaction
Runs a JavaScript expression with --eval before exporting the resulting page.
Automation Server
Serves CDP, WebDriver Classic, and WebDriver BiDi from one endpoint with moli serve, usable from Playwright.
Operational Controls
Configures profiles, cookies, proxies, resource policies, timeouts, and private-network policy.
Related Agents
BitFun
Runs an open-source desktop and terminal coding agent that plans, edits, tests, and reviews changes inside real Git rep…
Firefox DevTools MCP
Lets MCP clients automate and debug a local Firefox via WebDriver BiDi: navigate pages, fill forms, inspect network and…
Agent Device
Automates iOS, Android, HarmonyOS, TV, macOS, and Linux devices from AI coding agents through a CLI, MCP server, and ty…
Agent TARS
ByteDance's multimodal AI agent for desktop and browser automation — controls GUIs, browsers, and shell via vision and…