🛠️ All DevTools

[Other] WSL container is now available for public preview

Show HN: PMB – local memory for coding agents that shows if it is used

[Other] WATaBoy: JIT-Ing Game Boy Instructions to WASM Beats a Native Interpreter

[Other] A field guide to the modern front end for developers who hand-wrote HTML

[Other] What can you confidently guarantee about your software?

[Other] Building Principia for Windows XP

Reading the internals of Postgres: Database cluster, databases, and tables

[Other] Show HN: Running a vision model on every screenshot on-device hi author here, Screenmind is privacy first Microsoft recall alternative . It runs on gemma 4 which is one of the fewer models supporting vision audio and reasoning all 3, so your data never leaves you machine.<p>With screenmind you can keep a track of your timeline , how much time you spent on what..search any screenshot with any text on it.. and the coolest thing, you can chat with your screen history, like what did alex texted me on discord or did i received any mail from Microsoft, if it was on your screen , you can prompt it in the cha. and also you can make automations on top of it, like send me my whole day report on slack(it has integrations )..you can also write automation either though plain English for not so coders or use the python for devs who want to deep dive, and you can save voice memos(with a screenshot) with just a hotkey, and get you meeting transcribed and summarised(auto detects meeting)<p>the hardest part which i faced was keep running screenmind as a background service it would not have been not hard if chat feature didn&#x27;t existed, as running local model requires compute ..and keep analyzing screenshots continuously will keep all the resouces hogged up for that i came up with a perceptual has cache .. the three tier cache system reduces inference upto 40% for an average user(which is me)..and to reduce the inference time more i came up with three modes..fast balanced and accurate..where the tradeoff is between time and accuracy<p>for now i use it daily on my 4gb gtx 1650 with fast mode, works pretty fine also it would be much faster on high end machine , it also has a mcp server so you can just ask claude desktop&#x2F;cursor about the bug you saw in morning..<p>supports windows&#x2F;mac&#x2F;Linux<p>being upfront about rough edges , it is not extensively tested on mac and installation has some friction , for which i m working on one click installer thing<p>(reposting- i put up an earlier version a few days back, comments got flagged cuz of new account so couldn&#x27;t reply to any )<p>repo:github.com&#x2F;ayushh0110&#x2F;ScreenMind<p>curious about anyone have idea for how to approach multi monitor support

[Other] 🧑‍🚀 Authentication and authorization infrastructure for SaaS and AI apps, built on OIDC and OAuth 2.1 with multi-tenancy, SSO, and RBAC.

[Other] WASM on the JVM Ships Under the Bytecode Alliance

[Other] Show HN: Shacam for macOS – Screen sharing you can touch shacam is a macOS menu bar app that lets you quickly share images, windows, your iPhone or iPad over your webcam, and interact with them using your hands<p>you can use it as a virtual camera in video calls, screen recordings, and live streams<p>everything runs on your device, and nothing is recorded or ever leaves your computer<p>hope you have as much fun with it as I do!

[Other] Lore – Give your coding agent the decisions your team made

[CLI Tool] Herdr: Agent multiplexer that lives in your terminal

[Monitoring/Observability] Show HN: XSDR – Real-time event monitoring infrastructure for agents XSDR is a unified pipeline for monitoring activity on X and the web. I built it because I wanted my agent to do things based on real-time events that were taking place instead of polling the web or scheduling cron jobs.<p>With XSDR, you can trigger agentic loops based on real-time events. All you need is an API key, a webhook that can receive POST requests, and an idea of what you’re looking for.<p>It currently supports X and Firehose (aka a persistent web crawler).

Newly discovered spider builds spring loaded snare to catch ants

[CLI Tool] Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs Bash4LLM is a single-file Bash wrapper for interacting with LLMs from the terminal. I created it because I wanted something simple that worked without installing Python, Node, or any other runtime.<p>It uses only Bash, curl, and jq. You can send prompts, start a small chat, process files line by line, stream output, and save session metadata in JSON format.<p>I tried to make it safe and predictable: no use of the system &#x2F;tmp, no use of eval. Groq is supported by default, and other providers can be added with dedicated Bash scripts in the extras&#x2F;providers&#x2F; folder.<p>Example:<p><pre><code> echo &quot;explains the command: ls -l&quot; | .&#x2F;bash4llm</code></pre>

[Other] Show HN: NanoEuler – GPT-2 scale model in pure C/CUDA from scratch Hi everyone,<p>I started working on nanoeuler after the ban of anthropic&#x27;s fable because my ambition and dream is to work in the AI field in anthropic. The two interesting reasons that led me to create nanoeuler were (1) interfacing with llm does not mean understanding how they are composed and (2), working on llm with a very low-level layer to understand the correlation between parameters and data and growth of the model and how the GPU works and how some layers can be optimized.<p>So I started working on it with a research aspect by making nanoeuler grow more and more but doing one step after another starting from Shakespeare.txt and understanding what a text generation model understands at 23 million parameters. For example, nanoeuler at that number had understood that Name: started a line and wrote that line with sense.<p>I wrote everything in CUDA because I wanted to not use any intermediary between the model in training and inference and what it had to do. Then the use of SFT and much more, even if in small ways, were really useful to understand the various step to make an llm like a chatbot.Any feedback, help, or suggestions are absolutely welcome!

WinPE as a stateless harness for Windows driver testing and fuzzing

Computer-Aided Language Development in Nonspeaking Children (1968) [pdf] <a href="http:&#x2F;&#x2F;i.stanford.edu&#x2F;pub&#x2F;cstr&#x2F;reports&#x2F;cs&#x2F;tr&#x2F;68&#x2F;85&#x2F;CS-TR-68-85.pdf" rel="nofollow">http:&#x2F;&#x2F;i.stanford.edu&#x2F;pub&#x2F;cstr&#x2F;reports&#x2F;cs&#x2F;tr&#x2F;68&#x2F;85&#x2F;CS-TR-68-...</a>

[Other] Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding