Privacy Policy
Last updated: 18 November 2026
Summary
railreader2 does not collect, transmit, or store any personal data. No analytics, no telemetry, no accounts, no crash reports. The application runs entirely on your device by default.
There are two exceptions, both off by default and both under your control: the optional Vision Language Model (VLM) integration, which sends data only to an endpoint you explicitly configure (see Vision Language Model integration), and AI tools you connect to your library, which then read your notes and documents’ text and pass what they read to their AI provider (see AI tools).
Data stored locally
railreader2 stores the following data on your computer only, in the platform-standard application data directory:
- Configuration — your settings (zoom thresholds, colour effects, UI preferences) in a JSON file. The only personal information is the name you sign your notes with, if you choose one. RailReader2 reads your computer account's name to suggest it, and saves it only if you accept.
- Annotations and bookmarks — highlights, notes, and bookmarks you create on PDF documents, stored as JSON files in the application data directory.
- Recent files list — paths to recently opened PDFs, stored in the configuration file for convenience. These are local file paths only.
- Library search index — so that
File → Search Library can search every PDF you have opened, the
application keeps an index in the
libraryfolder of the application data directory. It holds a copy of the text of those documents (pages, outlines, your notes and comments, and comments others wrote into the PDFs), the title, author, subject and keywords stored in each PDF, their file names and locations, the page you last read, and small pictures of their first pages for the welcome screen. Password-protected PDFs are recorded by file name only: their text and pages are never stored. Settings > Library (advanced view) shows its size and can clear it; Remove from Library in the Library window forgets a single document. - AI tools settings — whether AI tools may read your library, and
the documents and folders you have hidden from them, in
ai_tools_prefs.jsonin the application data directory. When you connect a tool in Settings > Library > AI Tools, railreader2 also adds one entry, namedrailreader2, to that tool’s own settings (Claude Code, Claude Desktop or Codex), and removes it when you disconnect. - VLM settings (if configured) — the endpoint URL, model name, and API key you enter in Settings > VLM are stored in the same local configuration file. The API key is not transmitted to any party other than the endpoint you configured.
None of this data leaves your computer unless you connect an AI tool (see AI tools). Help → Clean Up Temp Files removes caches, temporary files and old logs; the library index can be cleared in Settings > Library. To delete everything the application has stored, remove its data directory:
- Linux:
~/.config/railreader2/ - Windows:
%APPDATA%\railreader2\ - macOS:
~/Library/Application Support/railreader2/
Network access
By default, railreader2 makes no network requests. PDF rendering, layout analysis (via the bundled ONNX model), and all other features run entirely on your device. The application does not send crash reports or usage statistics.
Network activity happens only in these cases, each of which you start or agree to:
- Update checks. On its first start the application asks whether it
may check for a new version once a day. Only if you agree (or choose
Help → Check for Updates) does it download a small, signed
release description from GitHub (
github.com), and, if you choose to update, the new version itself. These requests carry nothing about you or your documents beyond what any web request does (your IP address and the application version). GitHub’s own privacy policy applies to them. The Microsoft Store version does not check: the Store updates it. - Model and language-pack downloads. Optional layout models and OCR language packs are downloaded from Hugging Face only when you press their Download button in Settings.
- Vision Language Model integration, when you configure an endpoint and use it, as described below.
The MCP server that AI tools connect to (below) makes no network requests itself: it talks only to the program that started it, over that program’s input and output.
Vision Language Model integration
railreader2 provides an optional Copy as LaTeX feature (keyboard
shortcut Ctrl+L) and a corresponding CLI subcommand
(railreader2-cli vlm) that send cropped images of detected layout blocks
(equations, tables, figures) to an OpenAI-compatible Vision Language Model API for
transcription. This feature is disabled by default and requires
explicit user action to enable:
- Open Settings > VLM and enter an endpoint URL, model name, and (optionally) an API key.
- Press
Ctrl+L, use the context menu, or invoke the CLI subcommand to send a block to the configured endpoint.
You choose the endpoint. It may be a fully local server (such as Ollama or vLLM running on your own machine), in which case no data leaves your device, or a cloud API (such as OpenAI, Google Gemini, or any other OpenAI-compatible provider), in which case the cropped block image and prompt text are transmitted to that provider.
railreader2 is not affiliated with, and is not responsible for, any third-party AI service you choose to use. Before enabling this feature with a cloud endpoint, you should:
- Review the privacy policy and terms of service of the specific AI provider you intend to use. Different providers have very different policies regarding data retention, model training on user inputs, and data sharing.
- Consider the sensitivity of the documents you are reading. Cropped images may include copyrighted material, confidential content, or personally identifiable information visible on the page.
- Check whether your institution or employer permits sending document content to external AI services.
If you want the benefits of the feature without sending any data off your machine, use a locally hosted endpoint (Ollama, vLLM, LM Studio, or similar). See the VLM setup guide for options.
To disable the feature entirely, leave the VLM settings blank (or clear them via Settings > VLM > Reset). With no endpoint configured, railreader2 makes no VLM network requests and the keyboard shortcut becomes a no-op.
AI tools (MCP)
railreader2 includes an MCP server that lets AI tools such as Claude Code, Claude Desktop
and Codex read your library. It is off by default. Until you tick
Let AI tools read my library in Settings > Library > AI
Tools (or run railreader2-mcp enable), it refuses every request, even
from a tool that has been set up.
What a connected tool can read: your notes and comments (and others’ comments written into your PDFs), with their replies, authors and colour categories; your named bookmarks; the page text of the documents you have opened; and each document’s title, authors, file name and page count.
What it can never read: file paths or folder names, the PDF files themselves or any images of them, anything from password-protected documents, and anything from documents or folders you have hidden (Hide from AI Tools in the Library window or on the start screen’s recent documents, Hide a Folder… in Settings). The server only reads; it cannot change your documents, notes or settings.
Where it goes: what a tool reads becomes part of your conversation with it, and is sent to that tool’s AI provider (for example, Anthropic for Claude and OpenAI for Codex). Their privacy policies and terms apply, and railreader2 is not responsible for them. As with the VLM integration, consider the sensitivity of your documents, and whether your institution permits sending their content to an AI service, before connecting a tool.
To stop it, untick Let AI tools read my library: requests are refused from then on, including from tools that are already running. Unticking a tool’s switch removes railreader2’s entry from that tool’s settings.
Third-party services
railreader2 does not integrate with any advertising networks or analytics platforms. Its only third-party integrations are the user-configurable VLM endpoint and the AI tools you choose to connect, both described above and both off by default.
Children's privacy
railreader2 does not collect any data from any user, including children.
Changes to this policy
If this policy changes, the updated version will be posted at this URL. Since railreader2 collects no data, substantive changes are unlikely.
Contact
For questions about this privacy policy, open an issue on GitHub.