r0otie
Joined 8 months ago
Joined 8 months ago
It replaces sensitive values with fake but structurally valid ones before anything reaches the AI. The structure is preserved so the AI can still help. When you get a response back, paste it in and it swaps everything back to the real values.
Runs entirely in the browser. No server, no accounts, nothing stored anywhere.
What it catches: API keys (AWS, OpenAI, GitHub, Slack and more), passwords, IPs, emails, JWTs, connection strings, PII (SSNs, credit cards, phone numbers), AWS/cloud identifiers, UUIDs, MAC addresses.
Browser extension auto-redacts on paste across 30+ AI sites so you don't have to think about it. Also a VS Code extension and a web tool.
privatiser.net — free, 100% local.
It detects and replaces sensitive values with consistent pseudonyms — so the AI can still reason about your text (e.g., "these two servers share the same IP") without seeing the real data. Then you paste the AI's response back and restore everything with one click.
What it catches: API keys (AWS, OpenAI, GitHub, Slack, etc.), JWTs, bearer tokens, SSH keys, connection strings, IPs, domains, emails, phone numbers, credit cards, SSNs, AWS ARNs/account IDs, Azure/GCP identifiers, UUIDs, and 200+ keyword-based patterns for passwords, hostnames, usernames, database names, etc.
It also understands natural language context — "password is secret123" and "host set to prod-db.internal" both get caught, not just key = "value" syntax.
Everything runs locally in your browser. No servers, no telemetry. Available as a Chrome/Firefox (Firefox is currently pending review) extension and a web tool.
Would love feedback on patterns you'd want added or things it misses.