Summary

Lyra Exporter is an open-source, multi-platform AI conversation manager designed for users to efficiently organize and export chat logs from various AI services like Claude, ChatGPT, Gemini, and NotebookLM. It addresses the challenge of managing extensive conversation histories by providing powerful filtering, searching, and tagging capabilities, enabling users to quickly locate specific details such as images, thinking processes, and tool call outputs, thereby enhancing the utility and retrievability of AI interactions.

How It Works

The project employs a web-based application that loads conversation data primarily via JSON files exported from supported AI platforms or through an integrated companion browser script (Tampermonkey). It intelligently parses and unifies data from diverse sources, automatically detecting file formats and handling rich content like images, code artifacts, and tool usage. Core features include automatic branch detection for visualizing conversation evolution, a robust tagging system for message organization, and flexible Markdown export options that preserve formatting and metadata, offering a streamlined workflow for managing and analyzing AI dialogues.

Quick Start & Requirements

• Install/Run: Access the web app online at https://yalums.github.io/lyra-exporter/. For local development, clone the repository, run npm install, and then npm start.
• Prerequisites: The Tampermonkey browser extension is recommended for the companion script-based data fetching.
• Usage: The recommended workflow involves installing the Lyra Exporter Fetch script and using its "Preview" button on AI platform pages. Alternatively, users can manually export conversations as JSON from AI platforms and load them into the Lyra Exporter application.
• Links: https://yalums.github.io/lyra-exporter/

Highlighted Details

• Broad Platform Support: Manages conversations from Claude, ChatGPT (including full account exports), Gemini, NotebookLM, Google AI Studio, and SillyTavern.
• Advanced Search & Filtering: Real-time search across message content and titles, with filters for images, thinking processes, Artifacts, and multi-condition combinations.
• Conversation Branch Visualization: Automatically detects and visually represents conversation branches, allowing users to trace dialogue evolution.
• Rich Content Preservation: Intelligently parses and preserves images, thinking processes, code artifacts, tool calls, and citations within conversations.
• Tagging System: Supports custom tags (Completed, Important, Deleted) with cross-file statistics and selective export of tagged content.
• Security: Implements API origin whitelisting, file size limits (100MB), JSON validation, XSS protection, and local storage isolation.

Maintenance & Community

This project is described as a personal endeavor, co-created with Claude. No specific details regarding active maintainers, community channels (like Discord or Slack), or formal sponsorship were provided in the documentation.

Licensing & Compatibility

The provided documentation does not specify a software license. This absence makes it impossible to determine compatibility for commercial use or closed-source linking without further clarification.

Limitations & Caveats

The project is actively improving the mobile and SillyTavern experience, indicating these areas may still be under development. The multi-conversation export experience is also noted as gradually optimizing. The recommended data fetching method relies on a browser extension.