FreeAskInternet is a free, private, and locally running search aggregator and answer generation tool. It targets users seeking an alternative to cloud-based AI search engines, offering a privacy-focused experience without requiring GPUs or API keys. The primary benefit is a self-contained, cost-free AI-powered search and answer system.

How It Works

The system aggregates search results from multiple engines using a local searxng instance. It then crawls the content of these search result links and feeds them to a chosen LLM (initially ChatGPT 3.5, with support for Qwen, Kimi, ZhipuAI, or custom LLMs via Ollama/llama.cpp). The LLM synthesizes an answer based on the provided search result content, all processed locally. This approach avoids external API dependencies and GPU requirements, making it accessible on standard hardware.

Quick Start & Requirements

• Install via Docker Compose: git clone https://github.com/nashsu/FreeAskInternet.git && cd ./FreeAskInternet && docker-compose up -d
• Requires Docker and Docker Compose.
• Internet connection is necessary for the initial setup and for the free LLM APIs if not using local Ollama.
• Web interface available at http://localhost:3000.
• Official documentation and project details are available on the GitHub repository.

Highlighted Details

• No GPU or API keys required for core functionality.
• Supports multiple free LLM APIs (ChatGPT 3.5, Qwen, Kimi, ZhipuAI) and local LLMs via Ollama.
• Utilizes searxng for multi-engine search aggregation.
• Web and mobile-friendly interface.

Maintenance & Community

The project is in its early stages, with potential for bugs. Credits are given to ChatGPT-Next-Web, FreeGPT35, LLM-Red-Team, and searxng projects. No specific community channels (like Discord/Slack) or roadmap are explicitly mentioned in the README.

Licensing & Compatibility

• Licensed under the Apache-2.0 license.
• Permissive license allows for commercial use and integration with closed-source projects.

Limitations & Caveats

The project is explicitly stated to be in its "very early days," implying potential instability and bugs. Functionality is dependent on the availability and reliability of the various free LLM APIs used, and users may encounter issues related to IP restrictions or internet connectivity.