Skip to content
Alexc09Public

About

No description, website, or topics provided.

Resources

Stars

1 star

Watchers

0 watching

Forks

Latest commit

 

History

1 Commit

Folders and files

Repository files navigation

Hovr - Instant AI Summaries on Hover

A lightweight Chrome extension that delivers near instant, concise AI-generated summaries when you hover over links - News articles, GitHub repositories, Blog posts, Documentation pages...

Get key points without opening a new tab

Demo

🚀 Features

  • 🔍 Hover-to-Summarize - Get instant summaries by simply hovering over links
  • ⚡ Fast & Lightweight - Minimal delay, no page refresh required
  • 📌 Point Form or Paragraph Mode - Choose how you receive summaries
  • ⏱️ Custom Hover Delay - Control how quickly summaries appear
  • 🎯 Adjustable Summary Length - Control min/max output length
  • 🔐 Privacy-Friendly - No tracking, BYOK (bring your own key)

🛠️ Tech Stack

  • Backend: Python, FastAPI, Trafilatura
  • LLM: Gemini 2.5 Flash-Lite
  • Frontend: Chrome Extension (Manifest v3)
  • Dependency Manager: uv

📦 Installation & Setup

1. Clone the Repository

git clone https://github.com/Alexc09/hovr.git
cd hovr

2. Install Dependencies

uv sync

3. Set Up Environment Variables

Create a .env file:

GOOGLE_API_KEY=your_api_key_here

Add other API keys as needed if switching providers.

4. Start the Backend Server

uv run server.py

The server will start locally and listen for extension requests.

5. Load the Chrome Extension

  1. Open Chrome and go to chrome://extensions
  2. Enable Developer mode (top right)
  3. Click Load unpacked
  4. Select the chrome_ext folder

The extension is now installed.

✅ Usage

  1. Click the Hovr extension icon in Chrome
  2. Enable ✅ "Extension Enabled"
  3. Configure your preferences:
    • Hover Delay - Time before summary appears
    • Point Form Mode - Bullet points vs paragraph output
  4. Hover over URLs, and a summary will appear after the Hover Delay

🧠 Model Configuration

  • Default Model: Gemini 2.5 Flash-Lite

  • Pricing:

    • $0.10 / 1M input tokens
    • $0.40 / 1M output tokens
  • Quality: Fast with good reasoning for most use cases.

Change the Model

In server.py:

MODEL_NAME = "your-model-name-here"

✏️ Summary Length Customization

Inside server.py:

MIN_LENGTH = X
MAX_LENGTH = Y

This directly controls:

  • Minimum output size
  • Maximum output size

Works for both bullet-point and paragraph modes.

https://usehovr.app/

About

No description, website, or topics provided.

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages