n4ze3m/page-assist

Use your locally running AI models to assist you in your web browsing

What it solves

Page Assist provides a way to interact with local AI models directly within the browser. It eliminates the need to switch between a web browser and a separate AI application, allowing users to access AI assistance while browsing the web.

How it works

It is a browser extension that connects to local AI providers such as Ollama, Chrome AI (Gemini Nano), or any OpenAI API compatible endpoint (like LM Studio or llamafile). It provides two primary interfaces: a sidebar that can be opened on any webpage and a full-screen Web UI similar to ChatGPT.

Who it’s for

Users who run local LLMs and want a convenient, integrated browser interface to chat with their models or analyze the content of the current webpage they are visiting.

Highlights

  • Integrated Sidebar: Access AI assistance on any webpage via keyboard shortcuts or context menus.
  • Chat with Webpage: Ability to ask questions specifically about the content of the current page.
  • Broad Browser Support: Compatible with Chromium-based browsers (Chrome, Brave, Edge) and Firefox.
  • Privacy-Focused: Data is stored locally in the browser storage, and the extension does not collect personal data.

Related

  • Project
    nico-martin/gemma4-browser-extension

    A Chrome extension that runs the Gemma 4 model locally via WebGPU to provide a private AI assistant capable of browser tab management and semantic webpage interaction.

  • Project
    browser-use/web-ui

    A Gradio-based web interface for the browser-use library that enables users to interact with AI browser agents using a variety of LLMs.

  • Project
    alibaba/page-agent

    A client-side JavaScript library that embeds an AI agent into web pages for natural language DOM manipulation and automation without requiring headless browsers.

  • Project
    browser-use/browser-use

    Browser Use is an open‑source Python/TypeScript library that gives LLM agents full control over a real or cloud‑hosted web browser. It provides 31 browser actions as tools, supports custom functions, works with OpenAI, Anthropic, Google models or its own BU2 model, and offers three usage modes: a fully hosted cloud API, a CLI for existing agents, and a library you embed in your code. Ideal for automating web tasks, building AI assistants that browse, or researching LLM‑driven web navigation.

  • Project
    abundantbeing/hermes-browser-extension

    A Chromium side‑panel that connects to a Hermes Agent (local, remote, or cloud) to chat, send page context, manage multiple agents, and view tool activity. It’s a UI front‑end, not a standalone AI model.