ZiweiKnows is an open-source tool for Ziwei Doushu (Chinese astrology) that provides precise destiny chart generation and AI-powered interpretations. It targets users interested in traditional Chinese metaphysics, offering self-deployment and multi-LLM support for personalized astrological analysis and fortune prediction.

How It Works

The project leverages the iztro library for accurate Ziwei Doushu chart generation, employing the Zhongzhou School Anxing method. Core interpretations are powered by adaptable Large Language Models (LLMs), allowing users to integrate services like Kimi, Gemini, or Claude. Advanced features include AI-driven "Life K-line" visualizations for long-term fortune trends and structured outputs for annual and dual-chart analyses.

Quick Start & Requirements

• Primary install/run command: Clone the repository (git clone https://github.com/ruijayfeng/ziwei.git), navigate to the app directory (cd ziwei/app), and install dependencies with npm install.
• Non-default prerequisites: Node.js, npm. Requires LLM API keys (e.g., Kimi, Gemini, Claude, DeepSeek, or OpenAI compatible) configured via the application's settings.
• Deployment: Supports Vercel and Cloudflare Pages by forking the repository and configuring the build settings (Root Directory: app, Build command: npm run build, Output directory: dist).
• Links: GitHub Repository

Highlighted Details

• Precise charting based on the iztro library with the Zhongzhou School Anxing method.
• AI-driven interpretations in a traditional astrologer style, with structured output.
• Advanced analytical features including annual fortune trends, dual-chart (relationship) analysis, and a 100-year "Life K-line" visualization.
• Flexible LLM integration supporting multiple providers (Kimi, Gemini, Claude, DeepSeek) and OpenAI-compatible APIs.

Maintenance & Community

Specific details on active maintenance, core contributors, sponsorships, or community channels (like Discord/Slack) are not explicitly detailed in the provided README.

Licensing & Compatibility

Licensed under the MIT License, which generally permits commercial use and modification with attribution.

Limitations & Caveats

While supporting multiple LLMs, the README notes a preference for Kimi ("although not the best, it's my favorite"), which might imply potential performance differences or specific tuning for that model. The project relies on external LLM APIs for its core interpretation features.