Moli is a headless browser you run on your own machine or server for AI agents, web scraping and retrieval pipelines. It can read pages and execute JavaScript without spending resources on visual rendering for every request. Layout and rendering run only when a task needs them, such as capturing a screenshot or clicking at specific coordinates.
Built in Rust, Moli has its own browser engine with V8 for JavaScript and Servo/Stylo for CSS. Its runtime handles dynamic pages, iframes, workers, cookies and browser storage. That makes it useful for extracting content from sites that need JavaScript to produce meaningful results.
Page extraction can return Markdown, HTML, JSON or compact semantic text trees for a model to read. Visual tasks can produce viewport and full-page screenshots, paginated PDFs and CPU-rendered screencasts. Rendering is optional, so text extraction doesn't carry the same visual workload.
For existing automation workflows, Moli supports CDP, WebDriver Classic and WebDriver BiDi. Playwright connects through CDP, and Chrome DevTools can inspect live page structure and styles. The browser and automation server come in one binary, without a separate browser or driver installation.
Moli runs on Linux, macOS and Windows and is open source under Apache 2.0. The local browser works independently of Lexmount Browser, the separate managed cloud runtime built around it. Moli also supports persistent profiles, HTTP caching and proxies.
Claim this page and we'll verify you by hand. Moli gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Moli?Promote it
Something wrong or outdated on this page?
419Updated 6 months ago
macOS · Windows · Linux#Agent Skills#Browser automation#Guardrails
webctl is a local browser automation CLI for developers and AI agents that need to read websites and interact with pages. It runs Chromium through Playwright on macOS, Windows and Linux, and supports container deployment. Its main distinction is control over how much page information reaches an agent's context: you can filter results before the agent reads them.
11.3KUpdated 1 day agoMIT
macOS · Windows · Linux · Docker#Browser automation#Multi-user access#PII redaction
6.2KUpdated 4 months agoMIT
macOS · Docker#Agent Skills#Browser automation#Code execution
28.2KUpdated 1 day agoApache-2.0
Linux · Docker#Browser automation#Code execution#MCP
7.7KUpdated 3 days agoApache-2.0
macOS · Docker · Web#Browser automation
Steel is a browser API for developers building AI agents that interact with websites. It runs Chrome sessions locally or on a self-hosted server through Docker, so you can keep browser infrastructure on hardware you control. The code uses the Apache 2.0 license. Steel also offers a hosted service where browser sessions run in its cloud.
2.6KUpdated 6 days agoApache-2.0
#Agent Skills#Browser automation#Code execution
CamoFox Browser is a self-hosted browser server for developers whose AI agents need to browse sites that block ordinary automation. It builds on Camoufox, a Firefox fork that changes browser fingerprints inside the engine rather than through JavaScript patches. This approach targets detection systems such as Cloudflare and Google's bot checks.
bb-browser lets AI agents work through your local Chrome browser using the website accounts you're already signed into. It's for people building agents that need to research across websites or interact with authenticated pages without a separate API integration for each service. The project is open source under the MIT license.
Obscura is a headless browser engine for developers building AI agents and web scraping systems that need many independent browser sessions. Each session starts with fresh state, so cookies, logins, and cached data don't carry between tasks. It's written in Rust and runs without Chromium, with a smaller memory footprint intended to support more concurrent sessions per machine.
Webcmd is a local browser automation tool for developers building AI agents that repeatedly work with the same websites. It remembers what agents learn about a site and turns familiar tasks into reusable commands, reducing repeated page inspection and reasoning. It's open source under Apache 2.0.