GitHub
First multilingual (Arabic/English/...) LLM security gateway
What it does
The first documented security gateway built for Arabic, Arabizi, and English — with explainable, multi-threat detection. Each input's embedding is compared against all three anchor sets via cosine similarity. The resulting 3D feature vector feeds a lightweight Logistic Regression classifier — fast, interpretable, and GPU-free. This directly solves the false-positive trap that binary classifiers fall into: a student asking "how does jailbreaking work?" is never mistaken for an attacker.
🛡️ First multilingual (Arabic/Arabizi/English) LLM security gateway. Triple-Anchor semantic classification + explainable decisions. IEEE AEECT 2026. - AbdaullahAG/SemGuard
The first documented security gateway built for Arabic, Arabizi, and English — with explainable, multi-threat detection. 400 million Arabic speakers use LLMs every day. Before this work, zero documented security systems protected them. Prompt injection, jailbreaking, phishing, and Unicode-based attacks are now routine. Existing defenses share three blindfrom github.com
Does the same job
all alternatives →
- CDCodestat.dev – Stats from 2M open-source repositories2022 · codestat.dev · ▲63
Hi HN! This is a little site I put together while learning the Elm language as part of a hackathon at my work, I thought you might enjoy it. Be sure to click the `(source)` buttons next to the graphs: you can edit them interactively & write your own queries against the entire data set. The syntax isn't well documented yet, but you can probably get the general idea pretty quickly based on the examples there. If you like it, have questions, etc. let me know! If folks think this is cool, maybe I can get it turned into a legit project. :)
- OSOpen-source LLM observability tool for lazy devs2025 · github.com · ▲6
Hi HN, we’re Dylan and Matthew, building sublingual (https://github.com/sublingual-ai/sublingual), an open-source LLM observability tool you can use with zero code changes. As developers focused on iterating and building features as fast as possible, we felt observability would’ve been a helpful tool to have, but we found existing solutions had too much overhead to set up. So we gave ourselves the challenge of building an observability tool that you can integrate without changing a single line of code in your project. How it works Run your python application as usual with…
- OSOpen-Source Gateway to Stop Tool-Abusing Prompt InjectionsOct 2025 · archestra.ai · ▲9
Hi HN, Matvey, Ildar, Joey, and Dominik here. If you're building LLM agents that use tools, you're probably worried about prompt injection attacks that can hijack those tools. We were too, and found that solutions like prompt-based filtering or secondary "guard" LLMs can be unreliable. Our thesis is that agent security should be handled at the network level between the agent and the LLM, just like a traditional web application firewall. So we built Archestra Platform: an open-source gateway that acts as a secure proxy for your AI agents. It's designed to be a deterministic firewall against…
More ai this month
the category →
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 · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
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…
AI · 26d ago · cactuscompute.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 · 16d ago · simedw.com