Huntly is a self-hosted, AI-powered information hub designed to transform web browsing into actionable knowledge. It targets power users, researchers, and developers seeking to centralize, process, and leverage web content efficiently. The primary benefit is the creation of a personal, searchable knowledge base enriched by AI, accessible through a browser extension and integrated with various AI assistants.

How It Works

Huntly employs a multi-component architecture featuring a browser extension for content capture and a self-hosted server for processing and storage. The core approach involves using AI for summarization, translation, and intelligent content analysis via custom shortcuts. A built-in Model Context Protocol (MCP) server enables seamless integration with AI assistants like Claude and Cursor, allowing them to query the user's knowledge base, search archived content, and retrieve data from sources like RSS feeds, tweets, and GitHub stars. Web content is automatically archived and extracted using Mozilla Readability, while Apache Lucene with IK Analyzer provides powerful full-text search capabilities, supporting boolean operators and fuzzy matching. Data is stored locally in an SQLite database, ensuring complete data ownership.

Quick Start & Requirements

The recommended installation method is Docker Compose.

1. Install Browser Extension: Available on the Chrome Web Store.
2. Run Server:
   • Docker Compose (Recommended): Create a docker-compose.yml file using the lcomplete/huntly image, mapping port 8088 and a local volume (e.g., ~/data/huntly:/data). Run with docker-compose up -d. Watchtower is recommended for automatic updates.
   • Desktop Client: Download and install the Tauri-based application for your OS.
3. Configure Extension: Set the server address in the extension settings. Register an administrator user upon first access to the web application.

• Prerequisites: Docker (for Docker Compose), web browser.
• Links: Website, Documentation, Download.

Highlighted Details

• AI Content Processing: Leverages AI for summarization, translation, and intelligent analysis with custom shortcuts.
• MCP Server Integration: Enables AI assistants (Claude, Cursor) to access the knowledge base, search content, and retrieve RSS, tweets, GitHub stars, and highlights.
• Web Archiving: Automatically saves and archives web pages with content extraction via Mozilla Readability.
• RSS Feed Management: Centralizes feeds with intelligent categorization, OPML import/export, and full-text search.
• Powerful Full-Text Search: Apache Lucene with IK Analyzer for Chinese text tokenization, boolean operators, and fuzzy search.
• Social Media & GitHub Integration: Handles Twitter/X threads and preserves media; syncs GitHub stars with metadata.
• Privacy & Self-Hosting: 100% self-hosted with SQLite, Docker deployment, and full data ownership.
• Multi-Platform Support: Web app, Chrome extension (Manifest V3), and desktop apps (Tauri).

Maintenance & Community

The project is noted as being under "rapid development." Notable sponsors include Augment Code, JetBrains, TARESKY, and 抹茶. No explicit community channels like Discord or Slack are mentioned in the provided text.

Licensing & Compatibility

The project is licensed under the MIT License. This license is permissive and generally allows for commercial use, modification, and distribution, including within closed-source applications.

Limitations & Caveats

The project is under rapid development, suggesting potential for frequent changes and API updates. Users on macOS might encounter an issue where the Tauri desktop application is flagged as damaged, requiring a specific command (sudo xattr -r -d com.apple.quarantine) to resolve.