Show HN: Local personal data redaction for any AI tools(github.com)
github.com
Show HN: Local personal data redaction for any AI tools
https://github.com/sophia486/pii-gui
I built the desktop app that detects and redacts personal data (or PII) locally without sending any text to server. It supports rule-based filtering and AI model-based redaction (eg openai privacy filter). It's open source and free. Please check out the repo and https://pii-gui.vercel.app/
9 comments
Here are the benchmark results. You can check more details in the repo. openai/privacy-filter on Apple M1 Max
dtype 1k total 1k tok/s 8k total 8k tok/s
━━━━━━━━━━━━━━━━ ━━━━━━━━━━━ ━━━━━━━━━━ ━━━━━━━━━━━━━ ━━━━━━━━━━
fp32 620.52 ms 1,664 4,893.86 ms 1,689
──────────────── ─────────── ────────── ───────────── ──────────
fp16 654.56 ms 1,578 5,430.17 ms 1,521
──────────────── ─────────── ────────── ───────────── ──────────
q4 582.13 ms 1,776 4,635.39 ms 1,784
──────────────── ─────────── ────────── ───────────── ──────────
q4f16 648.10 ms 1,594 5,261.56 ms 1,570
──────────────── ─────────── ────────── ───────────── ──────────
quantized int8 573.94 ms 1,801 4,594.95 ms 1,800I would love to have an option where instead of just redaction; I'd love to swap it with something else when it goes to AI and then swap it back when the AI returns it. Thanks for sharing the github. I might submit a PR if I don't find that feature
I wanted to implement the feature initially. i realized that it requires modification of coding agents (eg codex, claude code, opencode etc). hook or skills pass PII data into server eventually so i decided to share the standalone app first. Feel free to submit a PR!
Nice, local is the right call. What's the local AI model — a small NER model bundled in, or calling out to something? Curious about the size/footprint for a desktop app.
It use openai/privacy-filter which is smaller than 1GB in size. I haven't checked usage during inference. It rans at 1k toks/sec on my macbook. I will update the repo with benchmark results. Thanks for the comment
Local is the way. Any benchmarks on latency it has on CPU?
I just ran the benchmark on my macbook. 582 ms for 1k tokens and 4.64 s for 8k