Your corpus never leaves your machine.
Uoink extracts video and podcast content, stores it on your disk, and hands it to the AI you choose. There is no Uoink cloud because we never built one.
What Uoink does.
Uoink captures transcripts, screenshots, comments, channel context, podcast transcripts, metadata, and local indexes. It writes those artifacts into normal local files and a local SQLite index. You can paste the corpus into Claude or ChatGPT, or let an MCP agent read it directly.
What Uoink skips.
No telemetry. No analytics SDK in the application or extension. No account. No phone-home. No hosted corpus. No remote logging.
Website analytics vs. local app privacy
While the local Uoink desktop application and browser extension collect absolutely zero telemetry, the public marketing website (uoink.video) uses basic, privacy-respecting Vercel Analytics to count page visits and help us see how people find the installer. No information from your local captures, library, settings, or API keys is ever accessible to or shared with website analytics.
Manual update check
When you click the update check button in the dashboard settings, the application makes a direct query to api.github.com to compare version tags. This request transmits no user details, telemetry, or library data.
Where your data lives.
On Windows, the helper lives under %LOCALAPPDATA%\Uoink. Captures write into your Uoink library folder. The optional Anthropic key is stored in Windows Credential Manager. On macOS, the planned path uses ~/Library/Application Support/Uoink/ and Keychain.
Network calls Uoink makes.
Extraction calls go to the source you asked for: YouTube, X, RSS hosts, or another supported URL. Optional Comment Intelligence, Hook Type, and Entity Extraction calls go to Anthropic with your key only when enabled. Nothing is proxied through Uoink.
Open source: audit it yourself.
The source is MIT-licensed at github.com/ryanbiddy/uoink. You can inspect the helper, loopback server, and network code.