My retired dad and I made a daily, somewhat difficult, quiz
My dad makes the questions, I made the site. I think the genre and the level of difficulty is suited for HN. Hope you enjoy. (I promise no AI-generated questions, they are all hand made!).
Filling PDF forms with AI using client-side tool calling
Hey HN! I built SimplePDF Copilot: an AI assistant that can interact with the PDF editor. It fills fields, answers questions, focuses on a specific field, adds fields, deletes pages, and so on. It's built on top of SimplePDF that I started 7 years ago, pioneering privacy-respecting client-side pdf editing, now used monthly by 200k+ people. As for the privacy model: the PDF itself never leaves the browser. Parsing, rendering, and field detection all run client-side. The text the model needs (and your messages) goes to whatever LLM you point at. By default that's our demo proxy (DeepSeek V4 Flash, rate-capped), but you can BYOK and point it at any cloud provider, or go fully local (I've been testing with LM Studio). Unlike the existing "Chat with PDF" tools that only retrieve the text/OCR layer, Copilot can act on the PDF: filling fields, adding fields (detected client-side using CommonForms by Joe Barrow [1], jbarrow on HN with some post-processing heuristics I added on top), focusing on fields, deleting pages, and so on. I built this because SimplePDF is mostly used by healthcare customers where document privacy is paramount, and I wanted an AI experience that didn't require shipping PII to a third party. Stack is pretty standard: - Tanstack Start - AI SDK from Vercel - Tailwind (I personally prefer CSS modules, I'm old-school but the goal since I open source it, I figured that Tailwind would be a better fit) The more interesting part is the client-side tool calling: events are passed back and forth via iframe postMessage. If you're not familiar with "tool calling" and "client-side tool calling", a quick primer: Tool calling is what LLMs use to take actions. When Claude runs grep or ls, or hits an MCP server, those are tool calls. Client-side tool calling means the intent to call a tool comes from the LLM, but the execution happens in the browser. That matters for: speed, you can't go faster than client-to-client operations and also gives you the ability to limit the data you expose to the LLM. For the demo I do feed the content of the document to the LLM, but that connection could be severed as simply as removing the tool that exposes the content data. The demo is fully open source, available on Github [2] and the demo is the same as the link of this post [3] What's not open source is SimplePDF itself (loaded as the iframe). I could talk on and on about this, let me know if you have any questions, anything goes! [1] https://github.com/jbarrow/commonforms [2] https://github.com/SimplePDF/simplepdf-embed/tree/main/copil... [3] https://copilot.simplepdf.com/?share=a7d00ad073c75a75d493228...
VisuaLeaf
Visualeaf is a MongoDB GUI I’ve been building over the past year. Stack is Electron + Angular + Spring Boot. There’s a live playground on the site if you want to try it without installing or putting in your connection (I provided one). The goal was to combine a visual workflow with the depth needed for real development work. Most existing MongoDB tools tend to optimize for either beginners or power users, but not both in the same interface. Core features: Query builder that supports full MongoDB query expressiveness + being able to drag and drop elements from the collection to the query builder Form based aggregation builder with synchronized JSON view Schema visualization and generation tools GridFS viewer with MP4 streaming support (streaming mp4 was pretty tricky ) IDE style split panels and multiple workspaces Import/export transformations (mask/edit fields during export ) Tree view ( finding a way to expand recursively thousands of nodes was a challenge) Table view (I had to build my own take on AG Grid focusing on optimizing horizontal and virtual scrolling to get it to scroll smoothly on thousands of rows and columns) A lot of the work ended up being performance engineering. It currently loads ~500MB of data into the UI in about 5 seconds on an M1 MacBook. And can even easily display over 20k documents of an average size (12kb) . Here’s a walkthrough of all its features:: https://www.youtube.com/watch?v=WNzvDlbpGTk Happy to answer questions! Thank you so much!
The Dominion List
Show HN: The Dominion List – an open-source db of Canadian founders in the US
Spec27
Hi HN! We’re a team of ML validation specialists and we’ve been building /Spec27, a tool for testing whether AI agents still do their job safely and reliably as models, prompts, tools, and surrounding systems change. We started working on this because a lot of current LLM evaluation work seems aimed at scoring general model behavior, while many teams are deploying systems that have a specific mission to fulfill. Many of the tools also assume you have full access to the agent stack and traces so you can place SDKs and Gateways, but a lot of agents are being created on vendor platforms where this isn’t possible. As a result, we approaches it from the outside in: all tests just run to the primary interfaces of an Agent and don’t assume anything about internals. The other important things about the approach is spec-driven. Instead of treating testing as a one-off benchmark or static eval set, we let teams define reusable specifications for the behavior they want from an agent, then generate tests against those specs. With this you can automatically generate adversarial and robustness checks, so you can see what an agent is sensitive to and what kinds of changes cause it to fail. We’ve worked on validation for other AI systems before, including vision and tabular workflows, and /Spec27 is our new product for language-model-based agents. Currently in early access, so we’d love feedback! The current version is strongest for single-turn agent and application validation. We do not fully support multi-turn interactions yet, and better telemetry/tool-call integration is still on our roadmap. We’ve made the product open to try for HN readers, with a sample flow so it’s easy to poke around without much setup. We’d especially love feedback from people deploying internal agents, vendor agents, or other AI systems where reliability matters more than benchmark scores.
Pu.sh
I originally was just messing with pi-autoresearch. Gave it a sample task to build the most portable coding agent. First cut was 6 KB of shell. Great for one-shots, unusable interactively. I was shocked it actually worked. Started building up -- adding features — but with a self-imposed rule: no new dependencies, and sub 500 LOC. This thing had to be truly portable. Just sh, curl, awk. System primitives only. Which means I did some genuinely disgusting things in awk, including JSON parsing and the OpenAI Responses tool loop with reasoning items carried across turns. It's now ~400 lines. In the box: Anthropic + OpenAI, 7 tools (bash, read, write, edit, grep, find, ls), REPL, auto-compaction, checkpoint/resume, pipe mode, 90 no-API tests. Not in the box: TUI, streaming, images, OAuth, Windows, dignity. Two honest things: 1. I stole/modified the system prompt and the architecture. Pi/Claude/Codex wrote the awk. I cannot read most of this code. This wasn't possible for me a year ago. 2. Heavily inspired by Pi (pi.dev) — same 7-tool surface, same exact-text edit model. Credit where it's due. Pi is awesome -- you should probably use them. The agent loop itself is tiny. Almost everything else in a "real" agent CLI is DX and hardening. You can probably build your own harness exactly how you like it. Mario Zechner's AI Engineer talk on taking back control of your tools nudged me here. The name is because it's a .sh file. The other thing it sounds like is, regrettably, also accurate.
GhostBox
Show HN: GhostBox – disposable little machines from the Global Free Tier.
Omar
We were both genuinely impressed by Claude Code after it helped each of us fix nasty CI problems overnight. Doing those fixes manually would have taken days. After that experience, we each found ourselves struggling through Ctrl+Tab through multiple Claude Code windows in our terminals. While we enjoyed having agents working for us in parallel, context switching and cycling through each terminal tab was a real pain. So we thought: Can we design a TUI dashboard that manages a large swarm of agents in one place? Even better, can agents manage agents hierarchically, like how companies work? OMAR (Open Multi-Agent Runtime) is the result of this exploration. We spent months building it, and we think it is now ready to show the world. If you find OMAR interesting, give it a try. We would love to hear from you. :) Check out our blog here for more details: https://omar.tech/blog/introducing-omar/ Thanks! Karim & Shaokai
Browser-based light pollution simulator using real photometric data
Hi HN — author here. iesna.eu is a browser-based ecosystem for working with photometric data: parsing standard luminaire files (LDT/EULUMDAT, IES LM-63, Oxytech, ATLA-S001), running design calculations against EN 13201 / ANSI/IES RP-8 / CJJ 45 / IES-IDA MLO, and (the part I most want to show off here) rendering real urban scenes in Bevy with the photometric data driving actual streetlight behavior, including sky-glow contribution. The Skyglow Analysis demo loads a real LDT file into a Bevy scene (Khronos Bistro test asset). The luminaire's intensity distribution drives the streetlight rendering directly — no fudging — and the sky-glow grade updates live as you adjust the uplight percentage. Swap to a full-cutoff fixture and the sky goes from F (Severe) back to A (Excellent). You can see the difference on the buildings as well as in the sky. Stack: Rust core (eulumdat-rs and friends, ~20 crates handling photometric formats), Bevy for the 3D rendering, WASM for browser deployment. No backend; everything runs client-side. About a thousand lines of new code on top of the existing photometric library to make the Bevy integration work. Things I'd love feedback on: The atmospheric scattering model is currently single-scattering Rayleigh+Mie. Is that defensible for the use case, or should I move toward multi-scattering? The Bistro test scene works well visually but isn't a controlled environment. Anyone know of a public urban geometry asset that's more typical of real road-lighting evaluation? The CJJ 45 implementation (China's national road lighting standard) is the only one I've had to reverse-engineer from translated PDFs. If anyone has primary-source experience with it, I'd value a sanity check. Open-source on GitHub (eulumdat-rs and the related crates). Crates.io: eulumdat
Mljar Studio
Hi HN, I’ve been working on mljar-supervised (open-source AutoML for tabular data) for a few years. Recently I built a desktop app around it called MLJAR Studio. The idea is simple: you talk to your data in natural language, the AI generates Python code, executes it locally, and the whole conversation becomes a reproducible notebook (*.ipynb file). So instead of just chatting with data, you end up with something you can inspect, modify, and rerun. What MLJAR Studio does: - Sets up a local Python environment automatically, runs on Mac, Windows, and Linux - Installs missing packages during the conversation - Built-in AutoML for tabular data (classification, regression, multiclass) - Works with standard Python libraries (pandas, matplotlib, etc.) - Works with any data file: CSV, Excel, Stata, Parquet ... - Connects to PostgreSQL, MySQL, SQL Server, Snowflake, Databricks, and Supabase. For AI: use Ollama locally (zero data egress), bring your own OpenAI key, or use MLJAR AI add-on. I built this because I wanted something between Jupyter Notebook (flexible but manual) and AI tools that generate code but don’t preserve the workflow. Most tools I tried either hide too much or don’t give reproducible results and are cloud based Demos: - 60-second demo: https://youtu.be/BjxpZYRiY4c - Full 3-minute analysis: https://youtu.be/1DHMMxaNJxI Pricing is $199 one-time, with a 7-day trial. Curious if this is useful for others doing real data work, or if I’m solving my own problem here. Happy to answer questions.
Large Scale Article Extract of Newspapers 1730s-1960s
Hello HN, over the past 7 months I've spent nearly 3,000 hours on building SNEWPAPERS, the first historical newpaper archive with full-text extractions, nearly perfect OCR, a vast categorization taxonomy and of course with semantic and agentic search capabilities. Problem: I wanted to search through newspaper archives, but when I tried every service only lets you search for keywords and dates, and gives you back raw images of the papers, and too many of them with no context. A sea of noise. Solution: I taught machines how to read the newspapers and so far I've extracted the content from > 600k pages (about 5TB) from the Chronicling America collection. Problems I had to deal with were an infinite variety of layouts, font sizes, image scan qualities, resolutions, aspect ratios, navigating around the images on the page. I also had to figure out how to get OCR to be nearly perfect so people wouldn't hate reading the extracts. I stitched together a multi-model pipeline (layout tech, ocr tech, llm, vllm) with heuristics to go from layout -> segmentation -> classification. I put it all in OpenSearch / Postgres and made it semantically searchable and also put an agentic search tool on top that knows how to use the API really well and helps you write queries to find what you're looking for. Happy to discuss AWS architecture and scaling as well, that was tough! If you have five minutes and you just want to jump in and have your own personalized experience, what I would suggest is: Before searching for anything, go to the Sleuth page Ask it about anything from 1736 to 1963, maybe 1 or 2 follow up questions Then go to the search page so you can see the queries it wrote for you (bottom left "saved queries") and uncover more info on whatever it is you're interested in If you think it's cool and you want to learn more, then there's about 10 minutes of video guides on the various capabilities in "Guide" on the nav bar Some other people have also taken a crack at this, notably: https://dell-research-harvard.github.io/resources/americanst... (very good attempt) https://labs.loc.gov/work/experiments/newspaper-navigator/ (focused on images)
State of the Art of Coding Models, According to Hacker News Commenters
Hello HN, I was away from my computer for two weeks, and after coming back and reading the latest discussions on HN about coding assistants (models, harnesses), I felt very out of the loop. My normal process would have been to keep reading and figure out the latest and greatest from people's comments, but I wanted to try and automate this process. Basically the goal is to get a quick overview over which coding models are popular on HN. A next iteration could also scan for harnesses that people use, or info on self-hosting or hardware setups. I wrote a short intro on the page about the pipeline that collects and analyzes the data, but feel free to ask for more details or check the Google Sheet for more info. https://hnup.date/hn-sota