AI PII & Secret Redactor
Strip emails, keys, tokens and personal data before prompting an LLM.
Text to sanitise
Nothing is uploaded — redaction runs in your browser
Drop a file here
Drop a log, transcript or prompt file
Redacted output
Pattern matching catches common formats but is not a compliance guarantee — always review the output before sharing.
About the AI PII & Secret Redactor
Scan prompts, logs and transcripts for emails, phone numbers, IPs, card numbers, SSNs, JWTs, private keys and API keys from OpenAI, AWS, Google, GitHub and Slack, then replace them with labelled placeholders, masks or stable pseudonyms that keep the text coherent for the model.
Examples
Redact an email
Contact ada@example.comOutput
Contact [EMAIL]Keyboard shortcuts
- Copy the main outputCtrl / ⌘ + Shift + C
- Download the resultCtrl / ⌘ + S
- Share this toolCtrl / ⌘ + Shift + S
- Reset the inputsAlt + R
- Open the tool search paletteCtrl / ⌘ + K
Related tools
AI Dataset Deduplicator
AI & LLM
Remove exact and near-duplicate rows from fine-tuning datasets.
AI Dataset Statistics Analyzer
AI & LLM
Profile a JSONL training set: token stats, roles, duplicates and cost.
AI Token Counter
AI & LLM
Count exact LLM tokens for GPT, Claude and Gemini prompts.
AI Tool Schema Builder
AI & LLM
Build function-calling schemas for OpenAI, Claude, Gemini, MCP and the AI SDK.
AI Tool Schema Converter
AI & LLM
Convert function-calling schemas between OpenAI, Anthropic, Gemini and MCP.
Chat Dataset Converter
AI & LLM
Convert between OpenAI chat, ShareGPT, Alpaca and prompt/completion.
Frequently asked questions
Read more
- How LLM tokens really work (and why your word count is a bad estimate)
BPE splits words, punctuation and whitespace into pieces. Here is how tokens are counted, why context windows overflow, and how to plan a prompt that fits.
Comments
No login needed. Comments appear after a quick review.
Loading comments…
Version 1.0.0 · Updated 2026-08-14 · Runs entirely in your browser