Alcatraz – Pure-Go PII detection, 100x faster than MS Presidio
Hi HN, I'm Andrios, founder of hoop.dev (YC W21), we build runtime controls for agents. We just released Alcatraz. We built it because our product is written in Go and we do real time Data Masking, but we were using MS Presidio (Python) for PII detection and it made connections slow. There was a good discussion here a few months ago when OpenAI released their Privacy Filter: (https://news.ycombinator.com/item?id=47870901). A lot of questions were built into our design. Structured identifiers (credit cards, SSNs, etc) are deterministic and you can verify them with checksum.…
What it does
In the maker’s words, at launch
Hi HN, I'm Andrios, founder of hoop.dev (YC W21), we build runtime controls for agents. We just released Alcatraz. We built it because our product is written in Go and we do real time Data Masking, but we were using MS Presidio (Python) for PII detection and it made connections slow. There was a good discussion here a few months ago when OpenAI released their Privacy Filter: (https://news.ycombinator.com/item?id=47870901). A lot of questions were built into our design. Structured identifiers (credit cards, SSNs, etc) are deterministic and you can verify them with checksum. Free text PII like names and addresses is where you actually need a model. Alcatraz started as our internal solution, but we wanted to make it available for everyone: in-process PII detection in Go. Currently 45 entity types across 12 countries (US and Brazil included). Benchmarks vs MS Presidio (lib to lib) about 13x faster on dense documents, 100x on smaller ones. Still in development, lots to improve. Feedback wanted: github.com/hoophq/alcatraz Edit 1: fix typo Python written as Phyton
Does the same job
all alternatives →
- OAOodle.ai – $10 per million agent tracesJul 2026 · oodle.ai · ▲31
Hi HN, we're Kiran and Vijay! Over the past two years, we have built a columnar storage engine for observability: logs, metrics, and traces. Today, it's exciting for us to show what we've built on top of that foundation: LLM Agent Observability. Given how non-deterministic agents are, storing all traces without sampling was critical for us. But these traces tend to be in the MBs, sometimes GBs - we needed to store them inexpensively. We also needed the queries and analyses to be fast. To meet both these goals, we store them in S3 in our own parquet-like file format, and query them using AWS…
- PDPII Detective, Leveraging LLMs for Cost-Effective PII Detection2024 · github.com · ▲6
PII Detective is a web application designed to identify, classify, and protect Personally Identifiable Information (PII) in data platforms such as BigQuery and Snowflake. It leverages LLMs to identify PII column names, and with human-in-the-loop validation, uses Dynamic Data Masking Policies to easily enforce Access Control Limits (ACLs) while minimizing user friction. For comparison, GCP has a "Sensitive Data Protection" service which promises similar functionality, but it can become extremely costly since it runs hundreds of regex queries on the entire contents of the table. For…
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 2d ago · opentrailpaper.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com