A cross-platform e-book reader built with Flutter that supports EPUB, MOBI, AZW3, FB2, TXT and PDF, with AI-assisted reading tools.
codedogQBY/ReadAny
Local-first AI e-book reader for desktop and mobile with RAG chat, semantic search, highlights, TTS and WebDAV sync.
Open-source alternative to:Apple Books
Kindle
- Stars
- 2,832
- Forks
- 227
- Open issues
- 378
- Last commit
- 12 days ago
What is it?
ReadAny is an e-book reader built around asking questions about what you read. You can chat with the current book or selected passages, and answers draw on your reading context, including your position, selected text and highlights. Search combines vector retrieval with BM25 keyword matching, so it can find concepts even when the exact word is absent.
The app stores books, highlights and notes locally, using local embeddings and a local vector store, so the library can work offline. It connects to OpenAI, Claude, Gemini, Ollama, DeepSeek and other compatible providers. Notes can be exported as Markdown, HTML, JSON, Obsidian or Notion formats, and libraries and notes can sync across devices over WebDAV.
ReadAny supports EPUB, PDF, MOBI, AZW, AZW3, FB2, FBZ, CBZ, TXT and UMD files. It is built with Tauri 2 for desktop and Expo (React Native) for iOS and Android, and includes text-to-speech, a reading heatmap and statistics.
Key features
- 01Chat with the current book or selected passages, with answers grounded in reading context
- 02Hybrid semantic and BM25 keyword search
- 03Local embeddings and local vector store for offline use
- 04Connects to OpenAI, Claude, Gemini, Ollama, DeepSeek and compatible providers
- 05Five-color highlights and Markdown notes with export to Obsidian and Notion
- 06Text-to-speech with Edge TTS, Browser TTS and DashScope voices
- 07WebDAV sync of library, highlights and notes
Use cases
- Asking questions about a non-fiction or technical book while reading it
- Building a private, searchable knowledge base from highlights across books
- Listening to books through text-to-speech during commutes
- Keeping a reading library in sync between desktop and phone
Quick start
- 1
Clone the repository
git clone https://github.com/codedogQBY/ReadAny.git - 2
Install dependencies (requires Node.js ≥18 and pnpm ≥9)
pnpm install - 3
Run the desktop app in dev mode (requires Rust)
pnpm tauri dev
Things to know
- Desktop development requires Rust, Node.js and pnpm, and mobile development also needs Xcode or Android Studio.
- Mobile development requires an Expo development build, since Expo Go is not supported.
- The README states GPL-3.0 licensing, so derivative works must also be open source under the same license.
Topics
FAQ
- What is ReadAny?
- Local-first AI e-book reader for desktop and mobile with RAG chat, semantic search, highlights, TTS and WebDAV sync. ReadAny is an e-book reader built around asking questions about what you read. You can chat with the current book or selected passages, and answers draw on your reading context, including your position, selected text and highlights. Search combines vector retrieval with BM25 keyword matching, so it can find concepts even when the exact word is absent.
- Is ReadAny free to use? What license does it have?
- ReadAny is open source under the Other license. Check the license terms before using it in commercial products.
- Is ReadAny still maintained?
- Actively maintained. The last commit to ReadAny was on Oct 7, 2026.
- What can I use ReadAny for?
- Asking questions about a non-fiction or technical book while reading it Building a private, searchable knowledge base from highlights across books Listening to books through text-to-speech during commutes Keeping a reading library in sync between desktop and phone
- How do I install ReadAny?
- Clone the repository: git clone https://github.com/codedogQBY/ReadAny.git Install dependencies (requires Node.js ≥18 and pnpm ≥9): pnpm install Run the desktop app in dev mode (requires Rust): pnpm tauri dev
- Where can I get ReadAny?
- The source code and installation instructions are on GitHub: https://github.com/codedogQBY/ReadAny
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Persistent memory for coding agents that captures session activity, compresses it with AI, and injects relevant context into future sessions.
Open-source Python web crawler that turns any website into clean, LLM-ready Markdown, with CSS/LLM-based structured extraction and an optional hosted API.
Compresses tool outputs, logs, files and RAG chunks before they reach an LLM, as a library, proxy or MCP server.
Open-source document parser that converts PDF, Office, HTML and other files into structured data for generative AI pipelines.
A self-hosted, OpenAI-compatible AI engine that runs LLMs, vision, voice, image and video models on any hardware, including CPU-only machines.