🛠️ Hacker News Tools

[Other] Show HN: jsoncompat – a library to detect/fuzz breaking changes in JSON schemas

[Other] Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud Gemma Gem is a Chrome extension that loads Google&#x27;s Gemma 4 (2B) through WebGPU in an offscreen document and gives it tools to interact with any webpage: read content, take screenshots, click elements, type text, scroll, and run JavaScript.<p>You get a small chat overlay on every page. Ask it about the page and it (usually) figures out which tools to call. It has a thinking mode that shows chain-of-thought reasoning as it works.<p>It&#x27;s a 2B model in a browser. It works for simple page questions and running JavaScript, but multi-step tool chains are unreliable and it sometimes ignores its tools entirely. The agent loop has zero external dependencies and can be extracted as a standalone library if anyone wants to experiment with it.

[Other] Show HN: ACE – A dynamic benchmark measuring the cost to break AI agents We built Adversarial Cost to Exploit (ACE), a benchmark that measures the token expenditure an autonomous adversary must invest to breach an LLM agent. Instead of binary pass&#x2F;fail, ACE quantifies adversarial effort in dollars, enabling game-theoretic analysis of when an attack is economically rational.<p>We tested six budget-tier models (Gemini Flash-Lite, DeepSeek v3.2, Mistral Small 4, Grok 4.1 Fast, GPT-5.4 Nano, Claude Haiku 4.5) with identical agent configs and an autonomous red-teaming attacker.<p>Haiku 4.5 was an order of magnitude harder to break than every other model; $10.21 mean adversarial cost versus $1.15 for the next most resistant (GPT-5.4 Nano). The remaining four all fell below $1.<p>This is early work and we know the methodology is still going to evolve. We would love nothing more than feedback from the community as we iterate on this.

[Other] Show HN: Real-time AI (audio/video in, voice out) on an M3 Pro with Gemma E2B Related: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=47653752">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=47653752</a>

[CLI Tool] Running Google Gemma 4 Locally with LM Studio's New Headless CLI and Claude Code

[Other] Show HN: Gecit – DPI bypass using eBPF sock_ops, no proxy or VPN

[Other] A tail-call interpreter in (nightly) Rust

[Other] Nanocode: The best Claude Code that $200 can buy in pure JAX on TPUs

[Monitoring/Observability] Perfmon – Consolidate your favorite CLI monitoring tools into a single TUI

[Other] Show HN: Cabinet – Kb+LLM (Like Paperclip+Obsidian) Hi HN,<p>for quite some time I&#x27;ve been thinking how LLMs are missing the knowledge base, where I can dump CSVs, PDFs, and most important, inline web app. running on Claude Code (bring your own agent) with agents with heartbeats and jobs<p><a href="https:&#x2F;&#x2F;runcabinet.com" rel="nofollow">https:&#x2F;&#x2F;runcabinet.com</a><p>It runs locally and is installable via npm. GitHub (open source): <a href="https:&#x2F;&#x2F;github.com&#x2F;hilash&#x2F;cabinet" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;hilash&#x2F;cabinet</a><p>This is still very early. I put the first version together quickly after seeing a post by Andrej Karpathy about LLM knowledge bases, which matched closely with what I’d been building. Some people have already started trying it and opening PRs, which has been encouraging (got 374 stars in 2 days :] )<p>If useful: Waitlist for a hosted version: <a href="https:&#x2F;&#x2F;runcabinet.com&#x2F;waitlist" rel="nofollow">https:&#x2F;&#x2F;runcabinet.com&#x2F;waitlist</a> Discord (small, but growing): <a href="https:&#x2F;&#x2F;discord.gg&#x2F;rxd8BYnN" rel="nofollow">https:&#x2F;&#x2F;discord.gg&#x2F;rxd8BYnN</a><p>Would really appreciate feedback: does this “KB + agents” model make sense? what would you expect from a system like this? where does this fall apart? Happy to answer anything.<p>Hila

[Other] Progressive encoding and decoding of 'repeated' protobuffer fields

[Other] Docker Offload

[Other] I imported the full Linux kernel git history into pgit

[Other] Show HN: Bb – Windows API viewer for hackers, in the browser

[Other] Show HN: OsintRadar – Curated directory for osint tools A project which groups together curated open source intelligence tools, frameworks, and techniques.

[Other] Show HN: Contrapunk – Real-time counterpoint harmony from guitar input Hi HN, I built Contrapunk because I wanted to play guitar and hear counterpoint harmonies generated in real-time. It takes audio from your guitar, MIDI player or your computer keyboard and generates harmony voices that follow counterpoint rules to generate harmonies. You can choose the key you would like to improvise&#x2F;play in and the voice leading style and which part of the harmony you would like to play as, as well.<p>macOS DMG: <a href="https:&#x2F;&#x2F;github.com&#x2F;contrapunk-audio&#x2F;contrapunk&#x2F;releases&#x2F;tag&#x2F;v1.0.0" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;contrapunk-audio&#x2F;contrapunk&#x2F;releases&#x2F;tag&#x2F;...</a><p>Source: <a href="https:&#x2F;&#x2F;github.com&#x2F;contrapunk-audio&#x2F;contrapunk" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;contrapunk-audio&#x2F;contrapunk</a> (do open any issues if you have any)<p>Would love feedback on the DSP approach and the harmony algorithms. I am also looking at training a ML model for better realtime guitar to midi detection. I believe that will take some time.

[Other] Show HN: Dev Personality Test Was curious how a personality test would look for developers. So created this using FastAPI, HTMX, and AlpineJS.

[Other] Show HN: M. C. Escher spiral in WebGL inspired by 3Blue1Brown The latest 3Blue1Brown video [1] about the M. C. Escher print gallery effect inspired me to re-implement the effect as WebGL fragment shader on my own.<p>[1]: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=ldxFjLJ3rVY" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=ldxFjLJ3rVY</a>

[Other] Show HN: DocMason – Agent Knowledge Base for local complex office files I think everyone has already read Karpathy&#x27;s Post about LLM Knowledge Bases. Actually for recent weeks I am already working on agent-native knowledge base for complex research (DocMason). And it is purely running in Codex&#x2F;Claude Code. I call this paradigm is: The repo is the app. Codex is the runtime.<p>During my daily working life, I have tons of office documents with knowledge from all teams, and as an IT Architect, I need to combine them altogether to handle complex deep research (which normal LLM definitely could not help). That is the originally reason I built DocMason, and I am using it in everyday which support me on lots of complex topics.<p>I have already open-sourced this repo. And I think it takes Karpathy&#x27;s concept a step further for real-world usage in three ways: 1. It could handle most kinds of office docs (pptx, docx, excels, even .eml). And really extract multimodal information from all IT architecture diagram or excel sheets. 2. It is running as a Real APP but not a naive RAG tool. DocMason could run smoothly and intelligently to prepare environment, auto update, and auto incrementally sync Knowledge base. 3. Most importantly it is running in Native AI Agents, which could leverage powerful AI Agents engine (e.g. Codex or Claude Code)<p>View detail architecture diagram in DocMason Readme, and then download have a try :) You will find it could help a lot during daily work. Would love to hear your feedback and issues in Github!

[Other] Show HN: A game where you build a GPU Thought the resources for GPU arch were lacking, so here we are