AgentCloak wants to keep your personal data out of AI prompts.
This is a AI post classified by Jev as AI productivity (a tool drop), kept by the AI Radar because it carries real work, not commentary.
AgentCloak wants to keep your personal data out of AI prompts. Its free browser extension uses a small AI model locally to detect names, account numbers and other personal data, replace them with placeholders before sending the prompt, then restore the originals in the response. Works with ChatGPT, Claude, Gemini, Grok, DeepSeek and more. No registration required. Would you trust a local model to protect sensitive data?
Posted by David Arnal (1.5k followers) 7 h ago · 0 likes · 56 views · view the original post on X. Kept by the AI Radar as AI productivity.
More AI work like this
- Every time I think “I wish my computer could do this,” it turns into another little… — @BkashJosi
- We found an AI tool that puts podcast production in one place, and now it's $200 for… — @nypost
- THERES A NEW CHATGPT IOS APP UPDATE!!!!!!!!!!!!!!!!!! — @nicdunz
- Made it to Canada. Where to next? 👀 — @Muse
- What happens when a global safety leader empowers 25,000 employees with secure,… — @GoogleWorkspace
- 我靠，ChatGPT 进 Word 真的太有用了！终于不用忍受 Copilot 了！ — @ScarletKc
- Building AgentCloak Desktop to protect your data from AI was fun. — @peteryared
- Today, we’re launching support for Chrome extensions in the ChatGPT desktop app! — @JamesZmSun
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 4.7k X accounts over the last 14 days, 1.3k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.