Clotr: AI chat privacy, clot your data leaks

Catches passwords, keys and personal details before you send them in AI chats and tools. Everything is checked on your computer.

Clotr warns you before you send a password, a key or a personal detail to an AI chat. You decide what happens next, and nothing you type leaves your computer. What it looks for - Passwords, API keys, tokens, connection strings and wallet seed phrases - Phone numbers, emails, addresses in the US, UK, Canada and Australia, and dates of birth, however they're typed, misspellings included - Card numbers, card security codes, gift card numbers, SSNs, bank accounts, IBANs, UK, Canadian and Australian account numbers, and several national ID numbers - Sign-in and backup codes that scammers ask you to read out, with a line saying who would really ask for one - Your own list (your name, your family, your street), kept only as a scrambled code, never the words themselves - Text inside files you attach, photos that still carry the place they were taken, and photos or files named for a seed phrase or backup codes It's on for 19 AI chats out of the box. Email and chat sites like Gmail, Outlook, Discord and Slack, search boxes like Google and Bing, and support chat widgets like Intercom and Drift are off until you tick them, on the welcome page or in Settings, and the browser asks you first. One more switch, "Everywhere I type", reaches a chat-style box on any website at all, not just the ones Clotr already knows; it's off until you turn it on, and Clotr only ever looks at a box that reads like a chat, never a form field holding your name, address, card or password. When it finds something, a warning appears in the corner of the page, naming what it found. You can cover the detail or send it as is. For the kinds you choose, it can ask before sending instead, or just count them. It only holds a message for the kinds you've set to ask before sending. Scam check looks out for you too. If a command you copy on an AI chat looks like the "verify you're human, paste this" trick, Clotr warns you before you run it and offers to clear it from your clipboard. Paste a message that worries you into "Is this a scam?" and it marks the signs it knows, in English or Spanish, and explains what each one means, without ever calling a message safe. Tourniquet gives stronger settings to someone you set Clotr up for, and after a scam or a near miss it can ask before money or an ID number goes out for 30 days, then step back down on its own. Practice lets you try spotting both safely, with made-up scam messages checked by the same engine that protects you, and made-up AI chat replies that show what would leak. A link you paste can carry a code you didn't mean to share: a code an app adds when you copy a share link, or a tag an ad network uses to follow the click. Clotr warns you by name and offers to strip just that part, with a page that explains what the code does and what Clotr can and can't see about it. Privacy Clotr has no AI inside it. It spots private details with plain pattern matching in your browser rather than asking an AI service, and there's no account, so only you ever see what it keeps. It has no network code, and a test fails the build if any is added. The history keeps only what kind of thing was found, on which site, when and what you did, and you can export or delete it. The code is open source (AGPL-3.0), and the build is reproducible, so you can check that the store's zip matches the source. Why it asks for each permission - Storage: your settings, your list as a scrambled code, never the words themselves, and the history (kind, site, time and what you chose, never the text), on this computer. - The AI chat sites: to check what you type in their message box, show the warning there, and swap a detail out when you choose to hide it. - Active tab: when you open Clotr on a site that isn't a known AI chat, it checks that one tab once to tell you whether it looks like one. Only on that click. - Scripting: runs that one check, and starts Clotr on a site you've added, or in AI chat tabs that were already open when it was installed or updated. - Declarative content: puts a small dot on the toolbar icon when a page looks like an AI chat, without reading the page. - Alarms: resets the toolbar's count for today after midnight, and removes history older than you chose to keep. - Other sites (optional): only the email and chat sites, search engines and support chats you tick, from a fixed list, or every website once you turn on Everywhere I type, and the browser asks you first either way. Made by Alex, a computer science student. The code, the issues and how to build it yourself are at github.com/clotr-app/clotr.