Alternatives
Products that do what Alcatraz – Pure-Go PII detection, 100x faster than MS Presidio does
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.…
- 1
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
27d ago · cactuscompute.com
- 2IP
The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol. Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day. A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship…
Mar 2026 · georgelarson.me
- 3
- 4LP
OP here. I built this because I recently caught myself almost pasting a block of logs containing AWS keys into Claude. The Problem: I need the reasoning capabilities of cloud models (GPT/Claude/Gemini), but I can't trust myself not to accidentally leak PII or secrets. The Solution: A Chrome extension that acts as a local middleware. It intercepts the prompt and runs a local BERT model (via a Python FastAPI backend) to scrub names, emails, and keys before the request leaves the browser. A few notes up front (to set expectations clearly): Everything runs 100% locally. Regex detection…
Dec 2025 · github.com
- 5MG
https://github.com/ncruces/go-sqlite3 was doing poorly on this benchmark that was posted yesterday to HackerNews [1]. With the help of some pprof, I was able to trace it to a serious performance regression introduced two weeks ago, and come up with the fix (happy to field questions, if you're interested in the nitty gritty). It's not the fastest driver around, but it's no longer the slowest: comfortably middle of the pack. It's based on a WASM build of SQLite, and thanks to https://wazero.io doesn't need CGO. [1]:…
2023 · github.com
- 6
- 7
- 8OA
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…
Jul 2026 · oodle.ai
- 9
- 10OC
Hi HN, I’m the creator of pycoClaw. I wanted to run OpenClaw-class, platform-agnostic, autonomous agents on MicroPython hardware, but standard tools couldn't handle the scale of the task. pycoClaw is the result, which bridges the gap between high-level AI reasoning and bare-metal execution. The Stack: - PFC Agent (~26k LOC): A full-featured agent that uses an LLM to 'self-program' its own local MicroPython scripts. Once a task is solved, it runs locally without requiring the LLM. - ScriptoStudio IDE: A PWA https://scriptostudio.com designed for the iteration speed required by…
Mar 2026 · pycoclaw.com
- 11
- 12
- 13
- 14GC
As I started to use Claude Code to do more random tasks I realized I could basically build any CLI tool and it would use it. So I built one that controls the browser and open-sourced it. It should work with Codex or any other CLI-based agent! I have a long term idea where the models are all local and then the tool is privacy preserving because it's easy to remove PII from text, but I'd definitely not recommend using this for anything important just yet. You'll need a Gemini key until I (or someone else) figure out how to distill a local version out of that part of the pipeline. Github link:…
2025 · cli-agents.click
- 15PD
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…
2024 · github.com
- 16AA
I'm a solo dev in Taiwan. I built 4 AI agents that handle content, sales leads, security scanning, and ops for my tech agency — all on Gemini 2.5 Flash free tier (1,500 req/day). I use ~105. Monthly LLM cost: $0. Architecture: 4 agents on OpenClaw (open source), running on WSL2 at home with 25 systemd timers. What they do every day: - Generate 8 social posts across platforms (quality-gated: generate → self-review → rewrite if score < 7/10) - Engage with community posts and auto-reply to comments (context-aware, max 2 rounds) - Research via RSS + HN API + Jina Reader → feed…
Mar 2026
- 17SH
Needed this in my own work, anonymizing PII/PHI and decided to build this because presidio didn't really cut it for our use-case. Try it and maybe let me know if you have any feedback :)
2025 · github.com
- 18IB
I had 14,000 photos sitting on a drive and wanted an excuse to play with local vision models and Elixir/Phoenix. I originally tried to get LLaVA to tell me if a photo was 'good' or matched my style, but quickly learned that LLMs have terrible taste. I ended up demoting the LLM to just extract metadata, and built a custom CLIP/Ridge Regression pipeline to actually learn my preferences based on how I rate things. The stack is Phoenix/Oban on the orchestrator side, and Python/FastAPI/Instructor for the AI workers. Happy to answer any questions about the architecture,…
Apr 2026 · qwelian.com
- 19CP
Hi hackers, long time reader, first time "real" submitter. This is by no means a revolutionary idea, or even execution, but rather something I've always wanted to do, just to see if I could write a good implementation of it. So without further adieu: http://ca.pitali.st/ Yes, it's just an URL shortener. Please check out the API and if there anything you like about it, please share, so I can take this feedback with me to my future projects. If there's something you REALLY hate, that's feedback too. Don't be afraid to hurt my feelings; this was put together in less than 4 hours to see if I…
2011
- 20IB
Hi HN! Since the launch of JigsawStack.com, we've been trying to dive deeper into fully managed AI APIs built and fine tuned for specific use cases. Audio/video transcription was one of the more basic things and we wanted the best open source model at this point it is OpenAI's whisper large v3 model based on the number of languages it supports and its accuracy. The thing is, the model is huge and requires tons of GPU power for it to run efficiently at scale. Even OpenAI doesn't provide an API for their best transcription model while only providing whisper v2 at a pretty high price. I…
2024 · github.com
- 21
- 22
- 23
Hi y'all. Been working on something that should've been made a long time ago imo. It compiles codebases into O(1) hashmaps that the agent queries to discover the structure of your code/answer questions/write code. It also does complete static analysis checks on any writes the agent makes. Don't take my word for it though. Here are the benchmarks: https://benzi.fly.dev/benchmark. on 2/20 tests, Claude Code (mostly Sonnet on one task) regressed or timed out. Benzi didn't because of course, it has a map it can query and not get lost in the sauce. On the other 18 it…
29d ago · benzi.fly.dev
- 24PA
We built PrivateClaw because the hosted OpenClaw platforms on the market today require you to trust them with plaintext. PrivateClaw removes that requirement at the hardware layer. PrivateClaw runs AI agents inside Trusted Execution Environments (TEEs), backed by AMD’s SEV-SNP standard. This means that your data is encrypted at the hardware level, enforced by the AMD Secure Processor outside the host OS trust boundary. PrivateClaw comes with inference that also runs inside TEEs, which means your prompts and completions are private as well. How it works: Each user gets a dedicated CVM…
Apr 2026 · privateclaw.dev
Ranked by how close each launch is in meaning, then by votes. Refine with a description →