Show HN: NodePad – AI agent on a canvas instead of a linear chat https://ift.tt/gTtZpc6

Show HN: NodePad – AI agent on a canvas instead of a linear chat https://node-pad.com/ June 30, 2026 at 07:47PM

Show HN: My 13-year-old built an ant colony tracker https://ift.tt/YoKwM72

Show HN: My 13-year-old built an ant colony tracker He's 13 years old. He wanted to track his own ant colonies — growth, feeding, humidity, and other metrics. He built the whole app himself with some help from AI tools; I just helped him deploy it to a server. Would love to hear your feedback! https://formicarium.es June 30, 2026 at 11:48PM

Show HN: fenic – LLMs as dataframe operators, query meaning and structure https://ift.tt/6DG5azb

Show HN: fenic – LLMs as dataframe operators, query meaning and structure Hey friends. I'd like to share a project that's dear to me. fenic is a dataframe API with LLMs added as first-class citizens, a classic lazy dataframe API extended with new operators that are backed by LLMs. What this gets you is the ability to work with structured and unstructured data in the same context. Most importantly, the LLMs aren't integrates as opaque UDF black boxes. They're exposed as "semantic" operators that the planner can reason about alongside the classic ones. (There are examples and code snippets on the repo to see how everything works together) Why build this? I'm a data infra / systems person. When LLMs showed up, what I saw was a new type of compute that changes the characteristics of the workloads we deal with. I wanted to experiment with how our current systems can absorb these new workloads and compute types, and what it would take to make the DX as seamless as possible, that's where the UDF + arbitrary prompt was feeling too problematic. To support this properly, we had to introduce a few really cool things: New plan operators. You don't just send prompts at an LLM. You use operators like semantic join, semantic map and reduce, and semantic filter, among others. They mix with the classic operators, and because the planner sees them as real operators rather than black boxes, it can reorder work around them. Typed outputs. There's ergonomics to turn the output of a semantic operator straight into a typed dataframe column. A Pydantic schema for the LLM output becomes a typed struct column you can unnest, explode, and so on. New data types like a markdown data type. Markdown became an important way to share information with LLMs, even though it started life as a way to format text for presentation. It carries structure, and being able to access that structure the way you would a struct or JSON type adds to the developer experience I mentioned. Async UDFs. One of the more interesting shifts in workloads from the LLM explosion is the need to put heavily I/O-bound steps in your pipeline: fetching a response from an API, crawling a website, and so on. Async UDFs fill that gap, and the implementation handles the nuances for you: concurrency, retries, and the rest. An LLM-inference-aware planner and runtime. This is one of the parts I'm most excited about, and there's a lot still to do. Today: identical prompts within a batch collapse to a single model call, so duplicates cost zero tokens; requests are dispatched concurrently under per-provider rpm/tpm limits with retries and backoff; null and empty cells skip the model entirely; and you get token and cost metrics per operator. There's also an optional persistent response cache so re-runs skip the model. MCP as a new catalog primitive. Much like a registered view, you can register a dataframe pipeline as an MCP tool in the catalog. fenic then serves an MCP server with that pipeline as the tool's logic, executed over your data. These are just some of what's gone into fenic while experimenting with how LLMs can become part of our compute infrastructure. There's more, and plenty more to polish on what's already there. I've been using fenic for all sorts of things. On the small/personal end, I use it to take my podcast audio recordings and turn them into nicely structured tables of metadata I can research. On the heavier end, I use it as tooling for agents to analyze agent traces exported from Pydantic Logfire, to discover evals and turn them into reproducible artifacts in the form of dataframe pipelines. pip install fenic Repo: https://ift.tt/VAiubM9 Docs: https://docs.fenic.ai There's also a skill you can use with claude code, codex etc. to quickly get started with fenic in your favourite agentic coding environment. I'd love to hear your thoughts, criticism, and anything else that comes to mind. I'm here to answer questions. https://ift.tt/VAiubM9 June 30, 2026 at 11:39PM

Show HN: Openleetcode – local LeetCode runner with open test suites https://ift.tt/cLrsW2p

Show HN: Openleetcode – local LeetCode runner with open test suites https://ift.tt/ztMyqw1 June 30, 2026 at 11:16PM

Show HN: The UNESCO Tsunami Warning Emails Are Gone https://ift.tt/ip9Kotv

Show HN: The UNESCO Tsunami Warning Emails Are Gone This key piece of tsunami warning and safety was discontinued this morning and evidently there's no way to get it back. :/ https://ift.tt/pBus8xG June 30, 2026 at 01:06AM

Show HN: Rust / Red Alert inspired WASM game in the browser (open source) https://ift.tt/jFaShpc

Show HN: Rust / Red Alert inspired WASM game in the browser (open source) https://punnerud.github.io/mpe-ra/ June 29, 2026 at 11:48PM

Show HN: HyperPaste – a free, open-source clipboard manager for macOS https://ift.tt/VqjPIrm

Show HN: HyperPaste – a free, open-source clipboard manager for macOS To me it always felt like clipboard history was one of the few things missing from macOS. There are already some excellent clipboard managers available, but after trying quite a few of them I kept coming back to the same goal: I wanted something that felt like it belonged on macOS. Fast, keyboard-first, private, and visually restrained. One thing I felt strongly about from the beginning was that it had to be open source. Clipboard managers have access to some of the most sensitive data we copy — passwords, API keys, personal information, financial details — and for something that sits in the background watching my clipboard all day, I personally wasn't comfortable using closed-source software. That ruled out a lot of otherwise great applications for me. The result is HyperPaste. HyperPaste is a free, open source clipboard manager for macOS, built with SwiftUI and AppKit. Clipboard data stays on your Mac — there are no accounts, cloud services, telemetry, or ads. Some highlights: - Instant search - Keyboard-first workflow - Rich support for text, code, links, colors, images, and files - Automatic color previews - Favorites for frequently used clipboard items - Native context menus and keyboard shortcuts - Local-first design with no ads or analytics One of the design goals was to avoid turning clipboard history into a productivity suite. I wanted HyperPaste to stay focused on one job: helping you quickly find and reuse things you've copied. The project is MIT licensed and the source code is available on GitHub. I'd genuinely appreciate any feedback, bug reports, feature suggestions, or criticism. I'll be around to answer questions throughout the day. https://hyperpaste.io June 29, 2026 at 10:13PM

Show HN: Sonar, local cited codebase briefings tailored to your role https://ift.tt/GTERy9V

Show HN: Sonar, local cited codebase briefings tailored to your role https://ift.tt/8hLglpq June 29, 2026 at 07:47PM

Show HN: NanoEuler – GPT-2 scale model in pure C/CUDA from scratch https://ift.tt/4bG8IU9

Show HN: NanoEuler – GPT-2 scale model in pure C/CUDA from scratch Hi everyone, I started working on nanoeuler after the ban of anthropic'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. 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. 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! https://ift.tt/RSq9ecG June 29, 2026 at 02:38AM

Show HN: Caliper – pass@k reliability testing for Claude Code and Codex skills https://ift.tt/XOrKvC8

Show HN: Caliper – pass@k reliability testing for Claude Code and Codex skills Skills for Claude Code and Codex are hard to test. What I mean by hard is that there's no standard way to do it. You evaluate the skill once on something, it looks like it works. You publish it. Then the new super model releases (GLM 5.2 anyone?), it will quietly break for some part, and you won't find out until your users complain. I also faced the same problem, so I tried to build something lightweight to stop doing that. Caliper. It's a local and lightweight harness that runs a skill k times in isolated environments and gives you a pass@k score (How much times it succeeded in these k times). As a non-deterministic technology, you can't just say "it worked once". You need to answer how much it passed in k times. You define success in a YAML spec. I picked YAML to keep a schema and make it still readable for a human. You either use a LLM judge, a Python assertion, or both: Here's an simple evaluation example with a JSON extraction, so you write this in a YAML file: tasks: - name: Extracts action items as clean JSON prompt: "Read /tmp/transcript.txt and write the action items to /tmp/actions.json." expect: "A valid JSON array where every item has owner, task, due. No markdown fences." assert: | import json items = json.load(open("/tmp/actions.json")) assert isinstance(items, list) assert all({"owner","task","due"} <= i.keys() for i in items) Then with the CLI, you'll run it: caliper run extract-actions.eval.yaml --k 5 --baseline What's cool about the --baseline flag is that it will re-runs everything without the skill, so you can see whether the skill is doing the work or the base agent was going to pass anyway: ID Task k(5) pass@k task-1 Extracts action items as JSON 5/5 100% PASS With skill 100% No skill 60% Delta +40% Most models know how to get the JSON right most of the time (JSON extraction was solved by 2 years old already). But that's it, "most of the time" is the bug. That delta shows how the skill actually helped. (It's sometimes 0%, sometimes -100%!) I also created two skills you can get started right away with your favorite harness, e.g. Claude Code, Codex or Pi: - evaluate-skill: run and manage evals without leaving your workflow - grill-skill: reads your SKILL.md, interviews you about what "good" looks like, writes a 3-task spec (happy path, edge case, adversarial), and runs it You can install the skill with the command: npx skills@latest add edonadei/caliper I for now support claude-code, codex, pi, claude-api, openai-api. You can run the agent and the judge as separate backends, so you can run a skill on one and judge with another. GitHub: https://github.com/edonadei/caliper PyPI: https://pypi.org/project/caliper-eval/ Of course, it's a first step. I think the autorater layer can be vastly improved, more handholding to create and iterate on evaluation specs, supporting more harness, why not including this layer into a self-improvement bigger system? If you're also building agentic evaluations, I'm genuinely interested to hear how you are handling that. https://github.com/edonadei/caliper June 29, 2026 at 12:42AM

Show HN: DRM-Free Books https://ift.tt/jC3fAq1

Show HN: DRM-Free Books After several years of mandatory DRM lockdowns from most commercial book sources, now authors have a choice when it comes to DRM for their books. Pick authors and books that are DRM-free, or download DRM-free classics that are out of copyright. https://ift.tt/Qd3FKU6 https://ift.tt/Qd3FKU6 June 28, 2026 at 11:58PM

Show HN: Starglyphs - A constellation puzzle game based on Euler paths https://ift.tt/uPFYsq4

Show HN: Starglyphs - A constellation puzzle game based on Euler paths I am a big Dragon Age fan and sunk hundreds of hours into Inquisition. It had this minigame called astrariums where you had to solve these shapes based on constellation guides by tracing stars. I'm a hobby game dev and wondered if I could procedurally generate these puzzles so they were always solvable. Turns out you can, so I built a space puzzle game around it with a colorful aesthetic. I released it in web form here but I'm currently working on getting it on Steam and mobile. https://starglyphs.com June 28, 2026 at 04:50AM

Show HN: Wind particles on Mapbox from a single EXIF JPEG https://ift.tt/PyalHx1

Show HN: Wind particles on Mapbox from a single EXIF JPEG https://ift.tt/PkTWzYt June 28, 2026 at 01:16AM

Show HN: A Living Neural Web in HTML5 Canvas https://ift.tt/JEuR8AZ

Show HN: A Living Neural Web in HTML5 Canvas https://techoreon.github.io/verpad/canvas-playground.html June 27, 2026 at 11:35PM

Show HN: Puzzle with Strangers. A free multiplayer jigsaw https://ift.tt/pN4ghfb

Show HN: Puzzle with Strangers. A free multiplayer jigsaw I built this over the last few days. Me and handful of friends are successfully hooked. I recently went to a — for lack of a better word – social/collaborative performance at an art gallery in Berlin where a group of artists filled a huge industrial hall with wooden 10x10cm cubes for people to build structures with. It was beautiful how universal the concept of playing with wooden blocks is and how ephemeral the structures were, people of all ages were put back into a childlike play. The thought about what kind of games need zero explanation stuck with me and i built an anonymous multiplayer jigsaw. We've already spent hours in there and you're invited now as well. Hope you enjoy. https://ift.tt/gMmKZRH June 26, 2026 at 11:47PM

Show HN: I built a hardware quantum RNG and wired it into a Magic 8-Ball https://ift.tt/D8gIXN3

Show HN: I built a hardware quantum RNG and wired it into a Magic 8-Ball Gday, author here! I've wanted to hack together a "real" quantum random number generator for another upcoming project, and I got carried away a bit, and went down the 'over-engineering' cliff. So, for your nerdy enjoyment, I have documented it all up, and I added something cool for fellow "Multiple World Interpretation" followers in the Quantum Mechanics debate. This QRNG uses sexy bits: Each is the decision of a photon to go left or right after hitting a 50:50 beam splitter. Standard kinda device, where you attenuate a light source down to single photons, offer them semi-mirror to bounce off, and see which PMT detector they hit (or which universe we ended up in ;) ). Basically, Through → bit=0. Bounce → bit=1. As I take the MWI interpretation of Quantum Mechanics (its the more fun options), I have also built a Quantum Magic 8-Ball. Ask it a questions, and you get and receive exactly one answer here, plus every possible answer across the multiverse. https://quantumlever.stream/oracle Enjoy! https://dnhkng.github.io/posts/building-the-beam-universe-splitter/ June 27, 2026 at 01:05AM

Show HN: A map of every UK railway, including stations that no longer exist https://ift.tt/uOrc5Hi

Show HN: A map of every UK railway, including stations that no longer exist Author here (Nathan). The goal for this site was to map the entire UK rail network: not just the parts a journey planner surfaces, but heritage lines, freight-only curves, named tunnels and viaducts, and the thousands of stations that have closed and were never mapped. The project is built entirely on open data. Lines and current stations come from OpenStreetMap via Overpass, closed stations from Wikidata (approximately 6,100 that fall outside a 250 m radius of a live OSM station), and postcode lookups from postcodes.io. The main challenge is that the sources rarely agree with one another, or even with themselves, so much of the work involved small reconciliation rules. For example, the heritage flag is propagated across every segment sharing a line name, so the Swanage Railway is coloured consistently. I shared an early version with a railway enthusiast community, and a large share of the fixes came from people who know the network considerably better than I do. A full write-up of the data challenges is available here: https://ift.tt/5dJPTvN No account or app is required. You can search by postcode, station name, three-letter code, or line name. Corrections are very welcome, as there is always a station someone knows I have got wrong. https://ift.tt/pYOXfT0 June 27, 2026 at 12:44AM

Show HN: Smart model routing directly in Claude, Codex and Cursor https://ift.tt/m5dw3QN

Show HN: Smart model routing directly in Claude, Codex and Cursor We built a model router that plugs into coding agents (e.g. Claude Code, Codex, Cursor, etc.) and intelligently sends requests to the best model to serve them. Here's a quick demo of running it locally: https://www.youtube.com/watch?v=isKhAyivtfM . At Weave, we write ~all our code with AI, and it's been getting more expensive. This came to a head when Opus 4.7 was released and, thanks to its tokenizer changes, our costs shot up. We knew we didn't need Opus for everything but we didn't want to lose out on the intelligence for the cases where you really need it. So we decided to build a model router to handle this for us. The Weave Router acts as an Anthropic/OpenAI endpoint specifically for coding agents. It looks at every inference request and intelligently (more on that in a sec) decides what model to send it to, handling all the translations required along the way. So it can use faster/cheaper models (e.g. DeepSeek v4, GLM 5.2, Kimi K2.6) when possible, and frontier models (Opus 4.8 & GPT 5.5 (& Fable whenever it's back)) when necessary. How do we know what model to route to? We trained an RL model on tens of thousands (so far!) of agent traces. We reward the routing model when it selects an LLM that successfully completes the given task. Here's an example: if you ask the router to plan a complex change, it will (probably) route that request to Opus 4.8. Subagents exploring the codebase to gather context will be routed to more suitable models (e.g. DeepSeek V4 Flash). Then when you have the plan ready to implement, it will be (most likely) be handed to a quicker model (e.g. GLM 5.2) to carry it out. We've been using this internally for the last month or so. We've saved 40% on tokens vs. what we otherwise would have paid, with no noticeable differences in quality or velocity. The router is source-available under Elastic License 2.0, so you can self-host it. Or if you prefer, you can also use our hosted version: weaverouter.com. I'll be here to answer any questions you may have! https://ift.tt/0EhpkNu June 26, 2026 at 11:40PM

Show HN: Hikaru Labs – Bulk image and file processing, 100% in-browser https://ift.tt/P0ngztS

Show HN: Hikaru Labs – Bulk image and file processing, 100% in-browser https://hikarulabs.xyz June 25, 2026 at 10:48PM

Show HN: Bible as RAG Database https://ift.tt/FuMYhno

Show HN: Bible as RAG Database Made this in a free evening. Index an permissive license translation of the Bible (WEB) into a RAG database to allow returning passages of similar semantic meaning. Lots of fun. For example, "more money more problems" returns Ecclesiastes 5:9-13 which, I'll just say, is spot on.. "Moreover the profit of the earth is for all. The king profits from the field. He who loves silver shall not be satisfied with silver, nor he who loves abundance, with increase. This also is vanity. When goods increase, those who eat them are increased; and what advantage is there to its owner, except to feast on them with his eyes? The sleep of a laboring man is sweet, whether he eats little or much; but the abundance of the rich will not allow him to sleep. There is a grievous evil which I have seen under the sun: wealth kept by its owner to his harm." Anyway - thought it was fun enough to share. It's slow and I vibe coded it so I haven't sorted out how to make it not take 15 seconds to vector search against the full 4GB index. https://ift.tt/OxhmjaJ June 25, 2026 at 08:42AM

Show HN: Top' for Redis Using eBPF https://ift.tt/bVuRtZQ

Show HN: Top' for Redis Using eBPF https://ift.tt/moIVgAh June 26, 2026 at 12:01AM

Show HN: iOS Apps on Linux https://ift.tt/isPmcQ9

Show HN: iOS Apps on Linux We developed and tested SwiftUI for Linux (and AppKit, NSFoundation, etc.) -- looking for more Swift apps to test on Linux! https://ift.tt/IgNSofv June 25, 2026 at 10:29PM

Show HN: DBOSify – Drop-in Temporal replacement built on Postgres https://ift.tt/LF6mgEb

Show HN: DBOSify – Drop-in Temporal replacement built on Postgres https://ift.tt/l0q4vRB June 25, 2026 at 12:20AM

Show HN: Metaspec: The DpANS3R Common Lisp Spec in S-Expr and HTML Format https://ift.tt/rjJQBqg

Show HN: Metaspec: The DpANS3R Common Lisp Spec in S-Expr and HTML Format I started this project back in 2015, to translate the TeX original specification into an easily parsed format (s-doc), and to create an HTML rendering of that format as a proof of concept. The project is homed here: https://ift.tt/TWe517g Differences from the Hyperspec (from the README): - Most importantly, it is free to modify and distribute. - The original TeX is very hard to parse and use for things other than generating a printed copy. The Hyperspec is an HTML rendering which can be parsed as HTML, but loses a lot of information. The Metaspec has an easily parsed intermediate form that can be used for all kinds of purposes, like converting into lookups. - Math equations are rendered using MathML. - Includes the acknowledgements and appendix sections. - Uses progressively enhanced Javascript to provide search and light/dark theme switching. - Incorporates over 145 patches for content, using corrections accumulated over the years, and documented in the errata page. - Includes TeX comments, which can contain interesting historical data. - Includes links and identifiers to bibliographical references. https://metaspec.dev/# June 24, 2026 at 11:28PM

Show HN: Forte – Cloud infra to get startups to production faster https://ift.tt/rcvXWRn

Show HN: Forte – Cloud infra to get startups to production faster Forte is an opinionated cloud platform that gets developers to production faster. Developers bring their code and Forte containerizes it with autoscaling and no cold starts, securely configures auth, and provides logging insights and monitoring out of the box. I used to help lead service development at AWS, and even before AI coding was widespread, our biggest bottleneck was rarely feature development. We would spend months on security prep, observability tooling, on-call optimization, and other overhead before launching new features. When I worked in startups, every team hit a surprisingly similar set of problems and spent weeks rebuilding auth, logging, monitoring, and payments. Platforms like Heroku, Render, and Railway are helpful for getting a container running but don't provide the rest of the tooling the teams need to go to production -- auth, secure defaults, and request-level logging. We built Forte to solve that entire stack of problems. You can check out Forte at https://ift.tt/jAQrPn7 (it's free to sign up and doesn't require a payment method). We'd love to hear your questions and feedback! https://ift.tt/jAQrPn7 June 24, 2026 at 11:06PM

Show HN: peerd – AI agent harness that runs entirely in your browser https://ift.tt/uIlsnDL

Show HN: peerd – AI agent harness that runs entirely in your browser Hey HN. http://peerd.ai is an AI agent harness that lives entirely in your browser as a web extension. You don’t have to install a separate “AI browser”. You don’t have to bolt on or run some external process or manage a clunky mcp integration. It’s just a fully contained web extension, written in no build vanilla JS with minimal non-browser dependencies, using your own provider keys, and Apache 2. This isn’t just a fun hack. While it has largely been a solo side project, I genuinely believe the browser and the web could be the most natural platform for AI agents to operate safely, autonomously, and most importantly without A2A middlemen (more on that in a sec). To demonstrate that point peerd doesn’t just drive browser automation. It spins up isolated sandboxes using tabs and worker instances to support various real workload types. Those include headless JS computational work, visual JS notebooks, personal client side apps, and real Linux VMs on top of wasm with full http networking. The industry discourse over the last several months has been dominated by “which substrate is the best for ai agent sandboxes” with many competing answers focused on different models and use cases. Cloudflare is one of the most prominent examples, positioning its v8 isolate based workers as the best in class solution thanks to faster than container startup times and strong isolation guarantees. The v8 isolate is of course the product of chromium, which runs on billions of browsers around the world for free. The browser as a whole is perhaps the most battle tested sandbox system in the entire software industry. It’s been built on 3 decades of learning from hostile content, hostile code, and hostile users. Native and cloud agents are necessarily rebuilding all or most of this posture from scratch. peerd doesn’t. It leverages everything the browser has to offer and pushes it to its functional limits, while inheriting its security baseline and isolation from the host system. Robust sandboxing isn’t the only thing the browser offers and peerd uses. It comes with extremely powerful and underrated primitives, from webCrypto, webRTC, webAuthn, webGPU, and ~soon WebNN. Direct web access, with your real live sessions, and api calls with fetch present an alternative model to MCP integrations. The agent can write and spawn web apps right there in a tab, no hosted service necessary. Then there’s the A2A piece: peerd already has a rudimentary p2p (peerd-to-peerd?) network in place using webRTC. Today you can connect with peers on the network, add them as contacts, and share signed apps you’ve created. I’m working on extending these apps to be able to leverage the same p2p network to support decentralized web apps (dwapps), as well as facilitate true p2p A2A with no platform or middlemen. Given this is an early part time project, this is an extremely experimental build and in a v0.x preview state. I’ve taken care to attempt to address the lethal trifecta: the main agent loops/sessions never ingest untrusted DOM code or possess low level navigation tools. It delegates those tasks to dedicated web runners with no wider tooling or secrets access that return summarized results. Both the DOM and the summarized results are bracketed as untrusted, meaning two stacked prompt injection escapes are needed. All egress goes through a central module that has a customizable deny list, and only models calls to designated allowed endpoints are possible. See more in the docs, site, and the code itself. Ultimately, use at your own risk. Today anthropic, open router, local ollama, and even an experimental WebGPU instance of Gemma are supported. Honest limitations: Chrome store and AMO are still pending until it can get more eyeballs and live usage. Just loading unpacked from GitHub is the easiest way to go, and as a bonus makes it easy to audit thanks to no build. Linux on wasm depends on the Cheerpx engine, which is not open source and has restrictions for commercial use. That may be a good reason to reassess it compared to alternatives, but it’s also the most performant and looks closest to implementing 64bit support. Poke around, use it, critique it, and have fun. https://ift.tt/yzLICVP June 23, 2026 at 10:05PM

Show HN: Caplets - Give your agent capabilities, not giant tool walls https://ift.tt/CoTcFYS

Show HN: Caplets - Give your agent capabilities, not giant tool walls https://caplets.dev June 23, 2026 at 11:31PM

Show HN: CUDA Profiler for Production Inference https://ift.tt/jFwhMz1

Show HN: CUDA Profiler for Production Inference https://ift.tt/9u7scD0 June 23, 2026 at 11:24PM

Show HN: I gave Claude Code the keys to the Visual Studio debugger https://ift.tt/JRsSwtu

Show HN: I gave Claude Code the keys to the Visual Studio debugger I use Visual Studio daily, and Claude Code only ships native integration for VS Code (annoying). So, I built the Visual Studio half myself. It's an unofficial extension that speaks Claude Code's undocumented IDE protocol. It started simple. Review Claude's edits in the real VS diff and accept or reject there, with no duplicate y/n prompt in the terminal, plus sharing the C# and C++ compiler errors with it directly. The infra I built for the extension allowed me to add the interesting part, the VS debugger. When you're paused at a breakpoint, Claude can read the call stack and locals, and with a toggle it can drive the debugger itself: set breakpoints, step, start and stop a session, and find a bug by running the code instead of reading it. There's a short walkthrough in the README where it catches a bug that never shows up in the output, by watching a counter fail to reset as it steps through a loop. Would really appreciate if you take the time to check it out. Thanks! https://ift.tt/qb5pOuN June 23, 2026 at 11:14PM

Show HN: Oak – Git replacement designed for agents https://ift.tt/RTpxg02

Show HN: Oak – Git replacement designed for agents Oak is a version control system I've been working on designed for agents ( https://oak.space ). It improves the speed and context your agents need when working on serious projects. With virtual mounts, agents locally and in the cloud no longer need a full copy of a repo to get working. You can work on many tasks in parallel without needing to download everything or fight worktrees. Version control shouldn't waste you or your agents time. It should be fast, creative and fun to make things with agents. Oak is still early in development. There's no Windows build and missing plenty of features (no CI, no issues, no comments). We still use GitHub Actions for building Oak now, but we've been fully bootstrapped on Oak with no Git backup for several months: https://oak.space/oak/oak . Blog post: https://oak.space/blog#git-is-forever Docs: https://oak.space/docs https://oak.space/oak/oak June 22, 2026 at 10:37PM

Show HN: Selector Forge – browser extension for AI-generated resilient selectors https://ift.tt/LT39K5g

Show HN: Selector Forge – browser extension for AI-generated resilient selectors Hi HN, I'm Ahmad from the Intuned ( https://intunedhq.com ) team. Today, we're releasing and open-sourcing Selector Forge ( https://ift.tt/2DBhQJc ), a browser extension that generates reliable CSS/XPath selectors using AI. You can use it to create a selector for a single element or for an array of elements. The selectors it creates are meant to be "semantic" and more resilient to page changes than what Chrome DevTool’s “Copy Selector” (and other similar extensions) give you. Those tend to hand you something brittle like `#top > div.w-100.ph0-l.ph3.ph4-m > h1 > span`, which can break with a minimal page change. Selector Forge aims for selectors that don't break as easily. Here are some selectors that Selector Forge created: `//div[@aria-label="Showing weekly downloads"]//p[@aria-live="polite"]` (item selector) and `//*[local-name()='svg' and @aria-label="Download statistics"]/following-sibling::div` (list selector). Here is a video demo of using the extension: https://www.youtube.com/watch?v=8IjjeDQkKmo Selector Forge on Chrome: https://ift.tt/wtPCTDm... Selector Forge on Firefox: https://ift.tt/BJUDVnq... Selector Forge code: https://ift.tt/1HtP4ub Backstory: For the past couple of years we've been building Intuned Agent, a coding agent for building and maintaining browser automations. We quickly figured out that the most fragile part of any browser code is usually the selectors and that creating good selectors can go a long way towards improving the quality and reliability of the automation itself. So we abstracted selector creation into its own agent, wrapped it as a tool, and let our codegen agent call it. LLMs by default don't do a great job generating good selectors, so this turned out to be really useful and improved the code our agent generates. We recently thought that this piece (the selector agent/creation) is useful on its own (outside our platform) so we packaged it as a browser extension. That’s this post! Selector Forge is open source, and the version in the browser stores (Chrome and Firefox) is free for up to 200 selectors/month. Unlimited usage is part of our paid plans. We realize most developers aren't writing this kind of code by hand anymore, so the next step is exposing this functionality in a way coding agents can call directly, over a CLI or MCP. Here's our roadmap: https://ift.tt/aUYsDTE Excited to hear your thoughts, questions, and feedback! https://ift.tt/1HtP4ub June 22, 2026 at 09:21PM

Show HN: React Native Boost – swaps RN's Text/View wrappers for native ones https://ift.tt/nihrMTw

Show HN: React Native Boost – swaps RN's Text/View wrappers for native ones https://ift.tt/2ePMjWq June 23, 2026 at 12:01AM

Show HN: Smolsonic – A Subsonic-compatible music server written in Rust https://ift.tt/HNyaFqP

Show HN: Smolsonic – A Subsonic-compatible music server written in Rust https://ift.tt/qOudRDA June 22, 2026 at 11:40PM

Show HN: DebugBrief – turn debugging sessions into reports, no AI https://ift.tt/Fhl5Ljz

Show HN: DebugBrief – turn debugging sessions into reports, no AI https://ift.tt/qou07P4 June 22, 2026 at 02:57AM

Show HN: CleverCrow: give tokens to your favorite projects https://ift.tt/X2xcPve

Show HN: CleverCrow: give tokens to your favorite projects Howdy all. I'm Zack :wave:. I've been thinking about the problem of misguided AI pull requests and figured I'd throw a possible solution out there for feedback. Basically, CleverCrow lets supporters give tokens to a GitHub repo (or set of issues in that repo) for the maintainers to use to build/fix stuff. The fun implementation challenges have been around implementing the pooling dynamics and keeping the maintainers in charge while the backers are motivated to support their work. https://clevercrow.io June 22, 2026 at 02:06AM

Show HN: Pulse – Dashboard for Claude Code, approve tool calls from your phone https://ift.tt/4HxnYp5

Show HN: Pulse – Dashboard for Claude Code, approve tool calls from your phone Hi everyone, I'm a student from Flanders and I like to use Claude Code for my purposes, ideas and also just for fun and also make solutions for problems in our world!) So that's why I built "Pulse", it's an local application that you can easily install to your device and easily follow what your claude agent is doing right now in your terminal session with an ambiance design and easily give permissions for your agent. For those who wants to see directly how much tokens you spent, and how much the session costs, and approve tool calls from everywhere from your phone and everything runs locally without an account can install Pulse from GitHub: https://ift.tt/1NtPnEF https://ift.tt/1NtPnEF June 21, 2026 at 03:46AM

Show HN: We post-trained a model that pen tests instead of refusing https://ift.tt/DZ437aX

Show HN: We post-trained a model that pen tests instead of refusing Anthropic and OpenAI's publicly available models are explicitly guard-railed so that they refuse offensive tasks. And their cyber-focussed models are gated for enterprises. This leaves SMEs and mid market open to major vulnerabilities. AI can be used as both an adversarial and defensive tool in the world of cyber. A worst case outcome is if only the adversaries have access. Meanwhile, most existing AI cyber tools are just wrappers. The problem is that they still have all the guardrails on from the foundation model where they will inherit its refusals. For this project we've post-trained a specific model on a decade of capture-the-flag contests. This won't be made available to anyone and everyone, but we do believe that responsible SMEs and midmarket companies also need access to these tools in order to identify key vulnerabilities in their systems; not just enterprises. We have developed two modes that run over a CLI: • Security scan: a read-only audit of your local codebase for vulnerabilities. It only reports what it can tie to a specific file and line, so you're not wading through vibes-based findings. • Pen test: an active adversarial mode that will try to break a live system in a sandboxed environment. It proves each vulnerability by running the exploit and showing the request it sent and the response your code gave back, not a confidence score. Currently gated. To show what the scan does, we pointed it at Bank of Anthos and it found an integer overflow in the transfer path: amount is an int, and amount + fee can overflow negative, so the balance check passes and you move funds you don't have. Plus the usual auth and secrets issues. (Bank of Anthos is Google's open-source bank. It's a known app and some of it is intentionally weak, which is the point: you can clone it and re-run the scan yourself instead of trusting a screenshot) The base model is a Kimi K2.6 (open weights). We didn't pretrain from scratch. We post-trained it ourselves, SFT on CTF writeups, then RL with verifiable rewards against actual exploit checks. How the harness works: Along with the model we built the harness to support this. The harness runs on a multi-agent swarm: an orchestrator splits the job across subagents running in parallel, each owning a slice, then synthesising one report. The CLI is a local binary (brew/curl). It reads your code locally, then sends context to our inference API over TLS tcpdump it and you'll see exactly what leaves and where. Install is free; and you can run a scan for free up to 2m tokens, then need to pay for tokens beyond this. For full disclosure this is a product part of Cosine (YC W23) Up for debate: tool safety, e.g. domain verification is one method that proves control but not necessarily permission. How would you gate a pen-test tool given that? https://ift.tt/VzytKNi June 20, 2026 at 08:49PM

Show HN: Microcrad – Micrograd Reimplemented in C https://ift.tt/tcEdeZo

Show HN: Microcrad – Micrograd Reimplemented in C https://ift.tt/CoUyhcj June 17, 2026 at 08:34PM

Show HN: Pagecast – Publish Markdown/HTML Reports to Cloudflare Pages https://ift.tt/wOaKu5F

Show HN: Pagecast – Publish Markdown/HTML Reports to Cloudflare Pages I built this because I kept generating HTML/Markdown reports from Claude Code/Codex and needed a permanent share link instead of a localhost tunnel. Pagecast is a local CLI that publishes those files to your own Cloudflare Pages account. It supports Markdown and HTML, stable URLs, renaming, republishing to the same URL, and watch mode for continuous updates to same file. It is MIT licensed. The main design choice is that there is no hosted Pagecast account. It uses your Cloudflare account and deploys there directly and has claude code and codex integrations as skill/hooks. Basically it can be used as a replacement for codex sites or claude artifacts https://ift.tt/kuGh0Ci June 19, 2026 at 02:42AM

Show HN: Metiq: a real time 3D globe for 100 public datasets https://ift.tt/PsauWA4

Show HN: Metiq: a real time 3D globe for 100 public datasets The concept for metiq.space came after playing Global Magnates with friends and realizing how fragmented live global data is. ships, aircraft, satellites, ports, weather, hazards, infrastructure, cyber, and public datasets all exist, but they usually live in separate tools and maps. The goal was to build one interactive 3D globe where live public data could be visualized by latitude, longitude, and altitude. Surface data stays on the globe, while aircraft, satellites, and other above surface things can be represented in actual 3D space instead of being flattened onto a map. The outcome is an interactive globe that showcases Earth, air, sea, space, cyber, defense, infrastructure, politics, and the list is continuously growing. Majority of development right now is going into data filtering and deduping. https://metiq.space June 16, 2026 at 09:43PM

Show HN: Run Agent Skills with mistral.rs v0.8.10: /v1/skills support and more https://ift.tt/aedgXWb

Show HN: Run Agent Skills with mistral.rs v0.8.10: /v1/skills support and more Hey all! I'm the maintainer of mistral.rs. I just landed support for OpenAI-compatible Agent Skills via a /v1/skills endpoint, and it works with local open models. Until now Skills have basically been locked to closed models, and with the ability to have private, local intelligence becoming increasingly important, but this feature allows you to do XYZ with local models. It's fully compatible with OpenAI's /v1/skills API, so you can drop mistral.rs into your existing code with minimal difficulty. We support the accompanying tools too: /v1/files or input_file for attaching files to your prompts, and mistral.rs also allows models to send generated files back using the OpenAI-compatible method. It's also easier than ever to try mistral.rs: we are including prebuilt binaries for NVIDIA CUDA, Apple Silicon, and CPU! # Linux/Mac > curl --proto '=https' --tlsv1.2 -sSf https://ift.tt/xm8ORu2... | sh # Windows > irm https://ift.tt/xm8ORu2... | iex Then: mistralrs serve --agent --isq 4 -m google/gemma-4-E4B-it Super excited for you to try this out and any feedback! Do you have any suggestions for what you would like to see in the next releases? Check out the GitHub: https://ift.tt/IkWJwRH Docs & Quickstart: https://ericlbuehler.github.io/mistral.rs/ June 18, 2026 at 02:03PM

Show HN: NGB, an open-source .NET platform for document-driven business apps https://ift.tt/7uhZEPp

Show HN: NGB, an open-source .NET platform for document-driven business apps https://ift.tt/VbwfzpM June 19, 2026 at 12:50AM

Show HN: SunCalc v2 – a tiny JavaScript library for sun and moon calculations https://ift.tt/2T8Nmvo

Show HN: SunCalc v2 – a tiny JavaScript library for sun and moon calculations SunCalc is one of my first open source projects — made the first commit 15 years ago and it had its share of wonderful uses ever since, but it's been somewhat neglected in recent years. Now that modern AI tools give me the ability to catch up on years of accumulated tech debt and user issues, I finally have the capacity to revive projects like this and keep them in excellent shape. v2 is a new version that improves the calculations accuracy by 5x for the Sun and by 20x for the Moon, verified by an extensive test harness vs ground truth from US Naval Observatory, in addition to fixing a ton of issues and modernizing the distribution with ESM. Hope you enjoy it. https://ift.tt/gnalUtw June 18, 2026 at 09:47PM

Show HN: The full Minecraft game as an embeddable Framer component https://ift.tt/cPJ2weG

Show HN: The full Minecraft game as an embeddable Framer component https://ift.tt/wlpUJWv June 17, 2026 at 11:43PM

Show HN: Deconvolution – a Rust image deconvolution and restoration crate https://ift.tt/jTGKhum

Show HN: Deconvolution – a Rust image deconvolution and restoration crate I've been working on deconvolution, a comprehensive Rust image deconvolution and restoration library. Deconvolution implements 28 different image deconvolution/restoration methods which range from practical blur removal techniques to research-grade scientific imaging algorithms. Features: - Top-level functions use image::DynamicImage and return images - Inverse filters, Wiener, Richardson-Lucy, constrained, proximal, Krylov, MLE restoration - Blind Richardson-Lucy, blind maximum likelihood, parametric PSF estimation - Kernel2D, Kernel3D, Transfer2D, Transfer3D, Blur2D/Blur3D - Gaussian, motion, defocus, microscopy models, support utilities, PSF/OTF conversion - Edge tapering, apodization, range normalization, NSR estimation - Deterministic blur, noise, synthetic fixture generation - ndarray support for 2D image arrays and 3D volume this project is a WIP, of course:) https://ift.tt/3Cyc6V4 June 15, 2026 at 07:40PM

Show HN: Ctx, save tokens by loading only the relevant tools https://ift.tt/ySa6hgT

Show HN: Ctx, save tokens by loading only the relevant tools Hi HN! Token cost has started to become a high topic of concern to all of us. I tried a few (awesome) tools such as rtk, caveman, and the recent (hillarious but effective) ponytail. What they usually do, is in-line token reduction, e.g. try to compress requests / responses as much as possible. But then it hit me (and I’m sure others had similar ideas) - just like we have routers that pick the right model, why not have something that will also narrow down the amount of available tools, skills and mcps based on repo/context? People usually accumulate skills, agents, MCP servers, harnesses, prompts, repo instructions, and local scripts. I’m not saying we are all hoarders, but we sort of are. When did you remove a skill recently? After a while, the model has way too many options to choose from. ctx tries to fix that by selecting context before the session gets bloated.So no, it doesn’t cleanup your messy garage, but it gives you magic glasses that let you focus only on the tools you need. It does it by watching the repo and task, walks a graph of available tooling, and recommends a small top-scored bundle of skills, agents, MCP servers, and harnesses. How does it know? To make sure results are not hallucinated, and repeatable, I curated a list of 91k+ skills, 467 agents, 10.7k MCP servers, 207 harnesses, and built a graph to help ctx make decisions on what to recommend. While I used AI to generate it of course, I curated it and revised it to make sure the data is up to date. So how this is different from rtk, caveman, ponytail, and similar token-saving tools? As mentioned above those tools mostly reduce tokens after something is already being used. rtk compresses command output. caveman-style tools make the assistant respond with fewer words. ponytail, is, well, awesome, but again it focuses more on reducing code (YAGNI) ctx is upstream. It tries to avoid loading irrelevant skills, agents, MCPs, and harnesses into context at all. So it is not really a replacement. It should work side by side with them! Use ctx to choose the right tools. Use rtk to reduce terminal-output noise. Use terse-output tools if you want shorter responses. The goal is simple: save tokens without forcing the user to manually test and compare thousands of possible skills, agents, MCP servers, and harnesses. Repo: https://ift.tt/eR65bBJ https://ift.tt/eR65bBJ June 17, 2026 at 01:14AM

Show HN: Microlearning apps with a TikTok-style feed to beat doomscrolling https://ift.tt/vNoinqD

Show HN: Microlearning apps with a TikTok-style feed to beat doomscrolling I wanted to kick my doomscrolling habit, so I built a microlearning app that uses a TikTok-style algorithm, same addictive feed mechanics, but you actually learn something. I started with a general version, Scroll: Daily Microlearning (microlearning.usescroll.app), but quickly realised it works better when focused on a single topic. So I split it into: Scroll: Personal Finance ( https://ift.tt/AN8chi7 ) Scroll: Learn AI ( https://ift.tt/QgZUTeu ) Scroll: Daily Microlearning ( https://ift.tt/STtqBjF ) https://usescroll.app June 17, 2026 at 12:06AM

Show HN: Claireon – MCP Server for Unreal Editor https://ift.tt/ZDPyUeJ

Show HN: Claireon – MCP Server for Unreal Editor https://ift.tt/JipYvef June 16, 2026 at 10:56PM

Show HN: Fata – Spaced repetition to fight skill rot from AI coding https://ift.tt/k3mWEvF

Show HN: Fata – Spaced repetition to fight skill rot from AI coding Hi HN, I'm Djoumé. I've been a developer for over 20 years, and like a lot of you I've been coding almost exclusively through an agent in the past few months. It's been amazing to vibe code prototypes in any stack, but when it comes to building something reliable/scalable, I couldn't effectively guide the agent unless I knew the technology. And the scariest part is that I'm seeing a lot of my technical skills decreasing due to AI coding. Reflecting on my journey, I also worry about how the new "AI native" generation of software developer is going to acquire technical depth. So I built fata.dev: short daily spaced-repetition sessions for programming skills (Rust, CSS, React, Python, TypeScript, Architecture). You can try it in the browser with no signup: https://ift.tt/9LiPlbU It's an offline-first mobile app built with Capacitor, RxDB and Firebase. The first courses were painfully written by hand, but most content is now AI-generated. It takes about 3000 LLM calls to generate a course, and every code samples goes through compilation, linting, unit testing, AI and a final manual review. Would very much appreciate any feedback on the product & website, what works and what could be better. Thanks! https://fata.dev June 11, 2026 at 06:57PM

Show HN: Steal-a-GIF – A browser tool to export GIFs from locked down platforms https://ift.tt/c2LZrWI

Show HN: Steal-a-GIF – A browser tool to export GIFs from locked down platforms Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this! https://vorpus.github.io/steal-a-gif/ June 15, 2026 at 09:28PM

Show HN: Trace – Offline Mac meeting transcripts you can flag mid-call https://ift.tt/cw5QiYk

Show HN: Trace – Offline Mac meeting transcripts you can flag mid-call I'm the developer of Trace, a non-intrusive, shortcut-driven Mac app that records and transcribes your meetings on-device. I know, another meeting transcription app. Please bear with me though, I'm confident that this is at least a little novel. I primarily built Trace for myself. I'd been using MacWhisper, but there was enough fiddling before each call that I'd forget to start it and walk out of an hour-long meeting with nothing written down. So the things I cared about most were that it's quick to activate and stays out of the way. You activate Trace by pressing a global shortcut (configurable), which reveals a small bar at the bottom of your screen (there's also a keystroke and/or option to hide it entirely if you'd rather not see it at all). As I was building it I wanted to bake in a couple of workflows I'd wished for in other transcription apps. 1. Mid-meeting you can press another global shortcut to mark a "key moment" and type a note. The note shows up in the resulting transcript inline at that timestamp. I wanted to add this because I kept catching myself thinking "wait, that bit matters" in meetings and reaching to jot it down in a separate app like Obsidian, which I then needed to add context to, which took me out of the meeting. I use it all the time. If I paste the transcript into an LLM afterwards (which I find myself doing more and more these days) the important moments are flagged so it doesn't gloss over them. This is more noticeable in longer meetings with lots of topics. 2. With another keyboard shortcut you can summon a rough live recap (subtitles, basically) to quickly recap what's just been said. Trace uses standard macOS microphone and system recording APIs to capture both sides of the conversation as two separate tracks and then runs the system side through on-device diarization to identify speakers. Right now we only label them as "Speaker 1", "Speaker 2", etc but there are plans for speaker labelling in the future. You can also show a "live recap" as the call is happening to review what someone just said. All transcription models run on your machine. To be clear though, Trace doesn't do any of the summarising itself, it just produces a markdown transcript, so if you want summaries then you need to pass the output to an AI. The app is sandboxed and your audio/transcripts are never uploaded anywhere - they just exist as audio files and markdown on disk. The only network call Trace is required to make is on the first run to download the speech and speaker models (around 500MB) from Hugging Face, and after that it can be used fully offline. If enabled, a Google Calendar integration can auto-name sessions but that needs a network connection. The app is £9.99 on the macOS App Store. I've been using it every day for months now and I'm super happy with how it's improved my workflow. Feedback very welcome. https://traceapp.info June 14, 2026 at 03:41AM

Show HN: Philosophy for Kids https://ift.tt/sfR0B35

Show HN: Philosophy for Kids Sometimes my son asks me 'why' questions that could be answered well by a kid-friendly philosophy article. But I don't know where to find those, so I ask Claude or ChatGPT, and have a specific workflow for getting the type of output I want. I figured other people might find those AI-generated articles helpful, so I put them here: https://ift.tt/CXTfUYl There's a search box at the top. https://ift.tt/CXTfUYl June 15, 2026 at 01:15AM

Show HN: Kage – Shadow any website to a single binary for offline viewing https://ift.tt/HbNfdCk

Show HN: Kage – Shadow any website to a single binary for offline viewing https://ift.tt/pEVFqol June 15, 2026 at 12:25AM

Show HN: Bye-wk – Hide World Cup news from your feed https://ift.tt/GuXJThM

Show HN: Bye-wk – Hide World Cup news from your feed https://ift.tt/AxYkg7z June 14, 2026 at 04:50AM

Show HN: Galdor – a Go LLM agent framework with built-in tracing and replay https://ift.tt/zdrDoWl

Show HN: Galdor – a Go LLM agent framework with built-in tracing and replay https://ift.tt/78aPKuH June 14, 2026 at 02:04AM

Show HN: Verso – A $14.99 Mac word processor with no subscription https://ift.tt/UnThsfp

Show HN: Verso – A $14.99 Mac word processor with no subscription https://ift.tt/o3AZWBx June 14, 2026 at 12:43AM

Show HN: Lightweight C++23 S3 client with no extra deps (just curl and OpenSSL) https://ift.tt/ykbOI0Z

Show HN: Lightweight C++23 S3 client with no extra deps (just curl and OpenSSL) Attached is my attempt at making a small toy S3 client without any other dependency besides libcurl and OpenSSL. Was tested mainly on MinIO (RIP) locally, so I would expect some bugs when using it against AWS, although I was able to play with it on some open access buckets Be aware that I am not a C++ programmer and this project was indeed done to learn a bit of C++ myself :') Feedback on any of the code, either on gtest, or the benchmarking section or the core itself is welcome! https://ift.tt/ebP4ZyX June 13, 2026 at 11:40PM

Show HN: Squishy & Friends – Claude Fabel 5 coded a game and it is good https://ift.tt/50zjLN6

Show HN: Squishy & Friends – Claude Fabel 5 coded a game and it is good https://ift.tt/NlmEtzq June 12, 2026 at 11:43PM

Show HN: 800x faster Linter and TypeScript-Go toolchain for plugins like typia https://ift.tt/PdG1XxF

Show HN: 800x faster Linter and TypeScript-Go toolchain for plugins like typia As a developer of typia, have to alive in the new typescript-go era, I made a new toolchain for tsgo. Making the ttsc, I understood that the new plugin toolchain system can dramatically reduce lint rule checking time by integrating into the typescript-go. So made `@ttsc/lint`, and its time is 600x to 1600x faster than eslint. From now on, when you compile TypeScript, lint violations would be caught in the same time. No more need to run both `tsgo` and `eslint` independently. > This repository is not v1 yet because the typescript-go has not been released yet, but if you wanna experience superfast lint, or keep using typia in typia era, you can do it right now. https://ift.tt/VSazOBY June 12, 2026 at 07:47PM

Show HN: Stillwind – High Resolution Electronic Component Search https://ift.tt/zticME5

Show HN: Stillwind – High Resolution Electronic Component Search We’ve spent the last couple of months building Stillwind Search, a search engine for electronic components that helps users find parts that fit even the most complex set of specifications. After talking to the people that actually build PCBs we found out that finding the exact part you are looking for, is consuming enormous amounts of times, is very tedious and then often doesn’t yield the best results. So we tried to cut down this search time by just requiring a (broad) description of the specifications and we find the correct part in minutes, not hours. This is possible through our own database of parts and their properties. We used LLMs to extract every parameter about a part into >1k schemas, collectively covering more than 130k properties. This depth of properties could no longer be visualized, so the database is queried interactively by an AI agent (Sonnet 4.6) to find the needle in the haystack of parts. Before results are shown, we use another model to verify the data (that’s why it might take a moment before the first results appear). We currently have almost all microcontrollers, sensors, and other advanced ICs on the market, as well as a wide selection of passives and generic parts. We are working on adding more parts and are more than happy to take suggestions. I know that folks on HN like technical details on how this works, so let me give a short overview: Frontend: SvelteKit + Cloudflare Workers + Hyperdrive Backend: PostgreSQL 18 (with io_uring) database, with extensions on NVMe drives hosted on a beefy server. We appreciate all feedback and are happy to answer any questions :) Btw: We are already working on a way that you can search combinations of parts, finding the optimal combination of parts. https://stillwind.ai June 12, 2026 at 01:12AM

Show HN: A police department for your Claude Code agents https://ift.tt/xYj1N2l

Show HN: A police department for your Claude Code agents https://ift.tt/sPqGC75 June 12, 2026 at 12:47AM

Show HN: AI Pair Programmer for Emacs https://ift.tt/kAWc2zY

Show HN: AI Pair Programmer for Emacs I built a pair programmer, using AI, but now am trying to go slow with new languages and paradigms using this package. I have noticed a decline in my programming skills, and wondered why I couldn't use AI as a pair programmer. Why can it watch what I'm doing over my shoulder and suggest changes? That way I can struggle through problems still and actually learn something. Results have been good so far :) https://ift.tt/6szjwKX June 9, 2026 at 01:34AM

Show HN: Extend UI – open-source UI kit for modern document apps https://ift.tt/3pDdbhi

Show HN: Extend UI – open-source UI kit for modern document apps We're open-sourcing 14 components & examples today for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more. It's MIT licensed and fully customizable. Demo video here: https://ift.tt/RpjqnhF When we started, we tried every file viewer and document component library we could find. Unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for https://extend.ai/ . It was only ever meant to be internal, but enough customers kept asking for it that we decided to open source it. It's useful for building document processing agents, real-time user facing document intake flows, or all kinds of internal tooling. We naively thought this would be a solved problem. Turns out, making PDF/XLSX/DOCX viewers that work at scale is not trivial...we use and maintain it for Extend ourselves, so we've fixed a lot of edge cases that came up while running millions of pages / day through our own system. Our hope is that with our resources + community support, it'll keep getting better over time. https://ift.tt/z5dAFqy June 10, 2026 at 11:09PM

Show HN: HelixDB – A graph database built on object storage https://ift.tt/KycINzd

Show HN: HelixDB – A graph database built on object storage Hey HN, it’s been just over a year since we launched HelixDB ( https://ift.tt/8Aj6s5m ), a project a friend and I started in college. It’s an OLTP graph database built on object-storage, with native vector search and full-text search (FTS). Why graph, vector and FTS? Graph databases provide a natural cognitive model for data, vectors allow for a semantic understanding of the entities and relationships in the graph, and FTS provides more specific filtering. Many AI-driven applications attempt to combine all of these functionalities by stitching together multiple disconnected systems, but even then there’s no native way to perform joins or queries that span all systems. You still need to handle this logic at the application level. Helix started as a graph DB, but we moved to a hybrid graph/vector approach after attempting to build an AI memory system, which led us down the GraphRAG and HybridRAG rabbit hole, where we would need separate graph and vector databases. We knew scalability would be a challenge at each stage of our product's development, however our initial focus this past year was to prove out the product through local deployments and was only meant to be run on a single node. Scaling graph DBs remained a difficult and expensive problem we’d have to solve later. Some common ways other graph DBs solve scaling is by duplicating entire datasets across distributed machines (extremely expensive per node), or by sharding the data. Sharding databases is effective and affordable, however, graph data doesn’t have explicit partitions like relational databases do. For example, sharding a relational DB involves splitting up tables. When it comes to graph DBs, the edges can span across any of the partitions, and hopping across multiple machines when traversing nodes is ineffective and computationally expensive. Replicating graph DBs for high availability and better throughput drastically increases the operational cost of the db and still has a limit of how big you can vertically scale. The workload that we’re used for requires storing a huge amount of data for agents, where only a subset of that data is ever needed at any one time. So rather than having the whole thing in memory, we can store it all in object-storage and get the bits we need when they’re needed. Agents benefit from better context, which is achieved from more and better data (more relationships etc). By using S3 as the persistence/data layer there is no limit to how big the graph can be or how many relationships you can have, and we can scale to serve throughput and requests by horizontally spinning up nodes and caching relevant subsets of the graph on each node. This way, you get extremely low latency for “hot” data and a p99 of ~100ms for writes and ~50ms for reads from cold storage (S3). Plus you get the benefit of dirt cheap storage. Workloads that HelixDB is currently supporting: - Huge amounts of data (TBs) from which the agents need to search and traverse over - Offering affordable graph storage for companies where cost of graph data is a bottleneck - Consolidating multiple databases, enabling AI agents to have autonomy over companies, helping them become more autonomous. - AI memory - Company brains We’re currently working on our own generalised AI memory layer which will use HelixDB under the hood and be completely open-source. Also, we’re finishing up on pre-filtering for vector search which will allow you to pre-filter based on relationships in the graph, metadata, and sub-graphs. And lastly, GA cloud will be available in the coming weeks. If you want to run Helix locally (either on-disk or in-memory), you can find more info on our github ( https://ift.tt/AZxd03I ) or via our docs ( https://ift.tt/fmApia8 ). If you’re interested in getting started with our distributed cloud, please email us founders@helix-db.com. Many thanks! Comments and feedback welcome! https://ift.tt/AJVGvBr June 10, 2026 at 10:47PM

Show HN: AI-native red-team for penetration testing and vulnerability research https://ift.tt/FzBkjDU

Show HN: AI-native red-team for penetration testing and vulnerability research AI-native red-team workbench for authorized penetration testing and vulnerability research, with specialist agents, sandboxed tooling, evidence records, and replayable timelines. https://ift.tt/pGt6qyO June 9, 2026 at 11:00PM

Show HN: A Minecraft builder skill for coding agents https://ift.tt/NoXY1vK

Show HN: A Minecraft builder skill for coding agents https://ift.tt/f4yTBDC June 8, 2026 at 09:51PM

Show HN: Gitdot – a better GitHub. Open-source, anti-AI, and written in Rust https://ift.tt/YTjnihx

Show HN: Gitdot – a better GitHub. Open-source, anti-AI, and written in Rust What works now: user signups, org creations, private/public repos, and importing GitHub repositories (both as read-only mirrors and full migrations). So basically, you can create, push and pull to a repo, but we don't have many features quite yet (issues, PRs, CI). What is a bit unique is: 1) we built it in Rust and 2) the website is a little odd. Its design is inspired by CLIs (e.g., fzf, broot, vim) instead of web apps, and as such, lacks some affordances that you might typically expect in favor of keyboard-driven instant navigations (we have the very ambitious goal of an FCP of 100ms). In case you're curious, here's how we we built it: https://ift.tt/sZrBjmF We recognize that we're making some bold claims here and are also well aware that we have much to learn. Building software is still hard, and that's a fact we seem to relearn everyday. But we wanted to share what we built so far nonetheless. Cheers, thank y'all for reading, and till the next —paul & mikkel. https://gitdot.io/ June 8, 2026 at 11:52PM

Show HN: Startup sci-fi novel that took me 5 years to write https://ift.tt/5Eo2mic

Show HN: Startup sci-fi novel that took me 5 years to write It started after reading Stephen King's "On Writing" where he likened the art of writing as the unearthing of an archeological site after you stumbled upon a unique bone of a story. His advice was to choose a domain you are deeply intimate with. For me, I've been a struggling startup founder for 15 years—enough material to inspire a novel. A 1,000-word writing exercise turned into a complete 125k-word manuscript over the course of a year. In year 1, I learned the sheer joy of unencumbered creative flow and authentic expression. A similar flow I used to get from coding (and more recently vibe coding). What made it effortless was a mindset that I was writing for the sake of it, not with the intention of publishing. After a year of keeping it close to my chest, I decided to show it to a few close friends. They liked some of it, destroyed some of it. Some ultimately encouraged me to publish it. In year 2, I learned about the chasm between writing for myself and writing for an audience. Nerdy stuff I thought were clever completely flew over my readers' heads. So I studied a dozen textbooks on literature, prose, poetry, voice, grammar, and completely rewrote the manuscript twice over, this time with the audience in mind. There is a lot more finesse to writing than I originally appreciated. In year 3, I felt ready to pitch literary agents. The reason wasn't to make a career out of writing, but to learn from professionals. After 100 personalized pitches and 0 offers of representation, I learned that pitching agents was much harder than pitching VCs. Especially for a niche novel like mine; fellow startup founders was too small of a TAM. In year 4, I engaged with a professional author/editor (Rob Hart, author of The Warehouse), who gave me essays worth of incredible developmental feedback. Lots of nuanced feedback I couldn't get from textbooks. Per his advice, I started back at chapter 1 and refactored the whole manuscript. I distilled it down to the best 88k words. The tinkering never stops; when do you know it's done? I realized that I kept on tinkering because it was more comfortable than overcoming the fear of launching. Today, on 06/08/26, almost 5 years after that Stephen King writing exercise, I'm ready to say “ship it.” Blockchained is a near-future startup sci-fi thriller that chronicles a struggling startup founder who meets a mysterious investor in Hong Kong. Little does he know that the too-good-to-be-true investor works for the Chinese government. Blockchained was written for the fellow startup founders, engineers, and near-future sci-fi enthusiasts. In other words, HN community, you are my target audience Sample chapters available at https://ift.tt/y4t6reR — eBook and paperback available today. Hardcover edition coming soon. I suppose we live in an era where it must be qualified that Blockchained was 99.9% lovingly handcrafted. No AI was used to write this novel aside from research, spellcheck, grammar, and the occasional phrasing checks. https://ift.tt/y4t6reR June 8, 2026 at 11:29PM

Show HN: Quick games disguised as boring spreadsheets https://ift.tt/VHqK6Gp

Show HN: Quick games disguised as boring spreadsheets I posted a version of this over a year ago but decided to rebuild it recently. Bored Spreadsheet is a collection of quick and easy games that look like a spreadsheet from a distance. I have tightened the app to be a collection of 6 games: Minesweeper, 2048, solitaire, sudoku, a market trading game and a daily reconciliation puzzle where the player must find bad data in a fake table. The games are free to play but sign up is required to submit your scores to the leaderboard. As was the original intention over a year ago, I hope this proves useful to those office workers who have a lot of downtime in between tasks or meetings yet don’t have the freedom to open Youtube or Cyberpunk 2077 on their work computers. Ironically my work network has blocked the website as it “contains non-business-related services” – I hope you have better luck than me! https://ift.tt/jXYrsSa June 8, 2026 at 11:13PM

Show HN: I Derived a Pancake https://ift.tt/U8yGDeE

Show HN: I Derived a Pancake After 25 years of making other people's pancake recipes - always yearning for more tang, more fluff, and more predictability - I decided to derive the pancake recipe from the chemistry. You mark checkboxes for what you have on hand (ricotta, sour cream, kefir, buttermilk, yogurt, cottage cheese, lemon, cream of tartar, etc.) and it computes the best recipe based on targets for acid, fat, salt, sugar, and CO2. My particular favorite are the yeast-raised lemon ricotta kefir pancakes - the best I've ever had. The math is done in a small pure-ESM library: ingredient composition to component masses and acid moles, a stoichiometry layer, and a bisection solver for the target deficits. I'm not a chemist, so if something is off, tell me and I will fix it! https://ift.tt/XQu43gC June 5, 2026 at 01:42PM

Show HN: Nightwatch, The open-source, read-only AI SRE https://ift.tt/EZitg5x

Show HN: Nightwatch, The open-source, read-only AI SRE nightwatch is a local-first, read-only layer on top of your monitoring. it groups alert storm into incidents, flags noisy checks and has an agent that can investigate for you live systems. You can e.g. jump from the incident into the agent directly. the reason for this weekend project is that we had a kubernetes upgrade that went wrong, and at some point a rollback wasn't possible anymore, so it had to be fixed live during the night while several problems came together. We run a lot of different systems, on-prem and several Kubernetes clusters, and in a situation like that you spend most of the time just figuring out what is actually broken and where. So i thought that it would be pretty cool to have eyes in the dark in each system that can talk to your "brain". so the idea is to put a baby owl into each environment. Each owl runs where the systems live, keeps that environment's credentials local, and only dials outbound to a central brain, so there is no inbound hole into prod. It exposes a set of read-only skills, and the agent uses them to gather evidence and form a root-cause hypothesis, so the on-call engineer starts with a head start instead of from zero. read-only for now, i don't trust it near prod yet and honestly neither should you. llocal-first for easy self-hosting and to keep credentials on your side. the clustering and recommendations run fully offline with no llm at all. the agent needs a tool-calling llm, you can point it at a remote one, or self-host one (ollama etc.) if you want to stay fully offline. for non selfhosters: before every remote llm call, nightwatch strips real secrets (unrestorable) and swaps identifiers like ips, hostnames and paths for reversible placeholders, so the model only sees masked data while real values are restored only in the proposed commands and tool calls Would love if you try it in your Systems https://ift.tt/WxHPig1 June 8, 2026 at 03:24AM

Show HN: OpenPayphone – open-source guts for a 1996 coin payphone (Pi and SIP) https://ift.tt/NPTph3I

Show HN: OpenPayphone – open-source guts for a 1996 coin payphone (Pi and SIP) https://ift.tt/JyqaELf June 7, 2026 at 11:36PM

Show HN: GentleOS – A pair of hobby OSes for vintage 32-bit and 16-bit PCs https://ift.tt/NrY8pLt

Show HN: GentleOS – A pair of hobby OSes for vintage 32-bit and 16-bit PCs Hello HN, I've been working on a simple OS for tinkering and running bare metal apps on vintage PCs. Since I couldn't quite decide whether to target pure 16-bit, or slightly more capable 32-bit machines, I ended up with two separate versions: - GentleOS/32 ( https://ift.tt/6jGvrMi ) works on i386+, requires 4MB of RAM and VGA display supporting 640x480x16 mode or any 256-color VESA mode. - GentleOS/16 ( https://ift.tt/DKEdljh ) works on 80186+, requires less than 192KB of RAM and a CGA display supporting 320x200x4 mode. You can find more details in the repos. https://ift.tt/6jGvrMi June 7, 2026 at 10:45PM

Show HN: Typedframes – Pandas/polars column name checking at lint time https://ift.tt/blBLuNg

Show HN: Typedframes – Pandas/polars column name checking at lint time https://ift.tt/WziVekB June 7, 2026 at 03:32AM

Show HN: Resonate – Low-latency, high-resolution spectral analysis https://ift.tt/LZCkxMu

Show HN: Resonate – Low-latency, high-resolution spectral analysis Last April I shared about my Resonate project here ( https://ift.tt/uGF07fQ ) A lot has happened since: the work I presented in much more detail at last June's International Computer Music Conference (ICMC) got best paper award. I also gave a talk at the Audio Developer Conference in Bristol last November, the video is on YouTube). This year's work, which I recently presented at this year's ICMC, starts with known techniques from the phase vocoder literature to build self-tuning filter banks that extract very efficiently the frequency components that are actually present in the input signal. Overview on the project website, more details in the papers, including applications to super-resolution spectrograms and re-synthesis experiments. As many people have pointed out, none of the techniques I have used are new (some of them even have different names across different fields), but I haven't seen them applied together in this way, and to me the results are incredibly satisfying and sometimes look magical. See for example this demo: https://youtu.be/LasdoIJJkw8 Of course the best way to experience in person is through the free demo app: https://ift.tt/k4V5jdU Looking forward to feedback from the community! https://ift.tt/Oxc31La June 7, 2026 at 01:09AM

Show HN: Ccgs – Collaborative Claude Code sessions, stored in Git branches https://ift.tt/a5LTeUx

Show HN: Ccgs – Collaborative Claude Code sessions, stored in Git branches My team uses Claude Code daily, and the sessions have become some of the most useful artifacts we produce. But they're trapped in ~/.claude/projects/ on whichever laptop they happened on. There's no good way to hand a colleague "the session where I untangled the migration" so they can claude --resume it and keep going from where I left off. Enter ccgs: Share Claude Code sessions through an orphan branch (@ccgs/) in your existing repo's remote - Session files carry the author's absolute paths. On pull, ccgs rewrites the working dir back to your path so resume actually works — surgically editing only the structural cwd field, not a blind find-and-replace that would happily corrupt the transcript. - Everything goes through git plumbing (hash-object/commit-tree/update-ref) against a throwaway index. It never touches your working tree, index, or current branch, and it's fine with a dirty tree. It will not git checkout something behind your back. To try it without installing: `npx claude-git-sessions`. This also incidentally allows you to move a directory and carry the claude code transcripts with it (just push first, then move the directory, then pull) IMPORTANT CAVEAT: Unless you have a very good security hygiene, your Claude Code sessions are likely full of sensitive information such as environment secrets. Use with caution and avoid using on public repositories. Branches used by ccgs are prefixed by `@ccgs/` so you can easily filter them out. This project was written by and with Claude Code. This Show HN was not. (Reposted with URL fixed) https://ift.tt/xXdmpH8 June 6, 2026 at 11:04PM

Show HN: Infinite canvas notes in the non-Euclidean Poincaré disk https://ift.tt/6AmawyR

Show HN: Infinite canvas notes in the non-Euclidean Poincaré disk Hi! This is an infinite canvas note-taking tool where notes are laid out in a non-Euclidean, hyperbolic geometric space. As you drag and navigate through the view, you’ll experience a unique fluid distortion that naturally leverages your brain's spatial memory. I’ve been obsessed with the concept of space in HCI for years. Many modern UI patterns are essentially workarounds for the lack of screen real estate. While researching zoom-based UIs a while back, I stumbled upon old HCI papers that used the Poincaré disk model of the hyperbolic plane to organize data. It elegantly projects an infinite space into a finite disk, keeping everything contextually visible. I wanted to build an experimental app around this concept years ago, but the non-Euclidean math was a significant roadblock. Recently, I decided to give it a shot with the help of LLMs. It turns out that LLMs can handle the mathematical heavy lifting quite well, specifically in designing the coordinate systems and optimization algorithms, provided that you guide them with a solid architectural design. This is still an experimental demo, but I hope it leaves an impression. I’d love to know if you find this paradigm practical for organizing your thoughts. https://uonr.github.io/poincake/ June 2, 2026 at 11:08PM

Show HN: Bash Runtime for AWS Lambda https://ift.tt/0D9N6PH

Show HN: Bash Runtime for AWS Lambda Hi HN, I built a Bash runtime for AWS Lambda to make writing glue code simpler and faster. Sometimes, all you need is a bit of `sed`, `awk`, maybe a loop and a few HTTP API calls, and this runtime gives you all the tools to do that. It comes bundled with `jq` and `curl` so you can handle JSON payloads and string together HTTP API calls right out of the box, including calling AWS services with `curl --aws-sigv4`. In keeping with the theme, the Lambda handler contract is also made as simple as practical: read from stdin, write to stdout, return 0 for success and non-0 for error. You can run shell scripts, call binaries (either what's available in `al2023.provided` or you can package your own static binaries with your handler), or a combination of both. If you remember nodding along to Adam Drake's post about how bash and coreutils can be faster than a Hadoop cluster, I hope you give this a whirl and find it useful. The runtime is packaged as a Lambda layer, so it should drop right into your normal AWS infrastructure. https://ift.tt/d7uwzFN June 6, 2026 at 02:12AM

Show HN: MimicScribe – transcriber with ~97% accurate on-device speaker IDing https://ift.tt/lVmoPIf

Show HN: MimicScribe – transcriber with ~97% accurate on-device speaker IDing I’ve spent the last seven months building a tool I wish I’d had in my previous roles. MimicScribe is a macOS menu bar app that fits the "AI notetaker" category. It has accurate on-device speaker identification (a first possibly?), real-time meeting talking points for discovery calls, and a fully keyboard- and voice-driven interface. I believe the accuracy of the speaker ID system is its biggest strength. I used fluid audio’s port of ( https://ift.tt/fPnWwcH ) Pyannote's community-1 as a base. To improve accuracy, the system uses grammar structure cues from the Parakeet STT to mask by sentence. By taking a second set of samples within that mask for cluster assignment, it leverages the fact that most people don’t finish each other's… sandwiches in business meetings. It tends to slightly oversegment, as I’ve found it much easier to merge segments or reassign a speaker than it is to untangle an incorrect merge. The app provides in-meeting talking points using a prompt tuned for discovery type calls. It can suggest probing questions to help you extract more detail or helps you refocus on the big picture with “magic wand” type questions (e.g. “how would your ideal system work”). Getting low latency models to provide novel, relevant, and totally not hallucinated information is a bit of a reach and it tends to restate the transcript frequently but little gems do come from it sometimes so it’s best to think of it as a source of inspiration and be a vigilant gatekeeper. It’s set up so recording can be started and ended via holding a keyboard shortcut instead of connecting to your calendar service. I prefer this for privacy and to keep transcript history from getting cluttered. Tapping the shortcut shows and hides an always-on-top overlay on your active screen regardless of whether you have other apps full-screen or not. Beyond simple navigation, you can also use voice commands to make post-meeting corrections or additions, for instance, you can simply say "merge this speaker with that speaker" to clean up the transcript. It also has push-to-talk/dictate functionality with LLM cleanup - what the app started as but that tool was developer catnip, soo many of them. A developer friend who’s worked in finance reviewed the site and said he’d bounce because the privacy story wasn’t strong enough so I added a completely on-device mode and a bring-your-own-key option. Using cloud models does add a lot to the experience, including context aware speaker merging and fragment cleanup, summary items during meetings, action items attributed, etc. On-device mode is completely free and the speaker identification is still very useful. The privacy story is my biggest worry with the app, particularly since its target audience is more technical people. I’d love to get people's thoughts on it and any feedback would be super helpful. https://ift.tt/3fU4FJ8 June 6, 2026 at 12:33AM

Show HN: SnapToCode – Screenshot any UI and get clean Tailwind code https://ift.tt/n8VrsZb

Show HN: SnapToCode – Screenshot any UI and get clean Tailwind code https://ift.tt/f9v8WSB June 6, 2026 at 12:05AM

Show HN: A Simplistic UI for Rich Hickey's Design in Practice https://ift.tt/JaBM034

Show HN: A Simplistic UI for Rich Hickey's Design in Practice For making it easier to iterate with an LLM on Decision Matrices. Try it: https://bmillare.github.io/design_in_practice_ui/ https://ift.tt/2FWYh6o June 5, 2026 at 11:09PM

Show HN: Bot or Not – Spot AI-generated randomness https://ift.tt/A19l3WZ

Show HN: Bot or Not – Spot AI-generated randomness https://play-bot-or-not.vercel.app/ June 5, 2026 at 02:56AM

Show HN: Cost.dev (YC W21) – making agents cost-aware and cheaper to call https://ift.tt/2iHZRVo

Show HN: Cost.dev (YC W21) – making agents cost-aware and cheaper to call We launched Infracost on HN five years ago ( https://ift.tt/qyGdZWr ) where our CLI generated cost estimates for infra-as-code, e.g. "this Terraform PR adds $400/mo". The idea was to shift cloud costs (FinOps) left, so engineers get visibility of costs before deployment and make better decisions. Earlier this year we started seeing agent traffic in our logs and it looked like coding agents were calling our CLI. But that CLI wasn't designed with coding agents in mind. We went down a philosophical rabbit hole to see if a CLI is even needed anymore given that Claude, Copilot et al. already follow best practices. Ultimately we decided to create a new CLI from the ground up with coding agents in mind for two reasons: 1. We optimized the CLI for agent callers and cut Claude's output token usage by up to 79% and API cost by up to 67% versus a bare-Claude baseline. We wrote a blog documenting our lessons on optimizing user token usage when designing a CLI, e.g. using predicate flags so the agent doesn't compose jq | python | wc pipelines, output format that strips JSON's redundant field names. The blog is here: https://ift.tt/8VK5JcQ... 2. With cloud costs, precision matters. Telling a coding agent "make this Terraform cost-optimized" can be expensive and lossy. You burn tokens loading code and policy context into every conversation. Your agent could make up a price and you wouldn't know because it's difficult to verify that across the ~10M price points that AWS, Azure and Google have. The CLI runs static analysis on the code, uses the latest prices from cloud vendors, and passes that context to the coding agent. So that's what we're launching today - Cost.dev: https://cost.dev/ . - It runs locally. Your code never leaves your machine, you get a fast feedback loop, and you're not burning API calls per character when you want to fetch prices. - The CLI does the deterministic work. Fetching price points, scanning the code, validating fixes. The coding agent does the natural-language part. You don't have to trust the LLM to remember the rules, and can verify it called the right CLI command. - It provides a consistent rule layer across every tool you use. Get cost estimates in your IDE and your coding agent with a single install. We support Claude Code, GitHub Copilot, Cursor, Windsurf, OpenAI Codex, Gemini CLI, as well as IDEs like VS Code and JetBrains Before we keep building more in that direction, I want to sanity-check with HN: is "agents writing IaC in prod" actually a thing yet, or am I betting on a future that's still a year out? I know software developers are using coding agents heavily, but are platform/infra folks doing that for prod too? Also, if you have any feedback on Cost.dev, I'd love to hear it! https://cost.dev/ June 4, 2026 at 06:30PM

Show HN: ClearLogo – a logo API that returns usable logos, not raw files https://ift.tt/MhH1tZO

Show HN: ClearLogo – a logo API that returns usable logos, not raw files https://ift.tt/Tdn6avw June 4, 2026 at 09:28PM

Show HN: Capture, compress, and copy screenshots to clipboard https://ift.tt/YKqU1mH

Show HN: Capture, compress, and copy screenshots to clipboard https://ift.tt/TvaPJAE June 3, 2026 at 11:46PM

Show HN: Rscrypto, pure-Rust crypto with industry leading public benches https://ift.tt/DpJAUM5

Show HN: Rscrypto, pure-Rust crypto with industry leading public benches https://ift.tt/I7y69Rb June 3, 2026 at 11:41PM

Show HN: Nutrepedia – nutrition info in 29 locales built with Clojure and Htmx https://ift.tt/axtuSDy

Show HN: Nutrepedia – nutrition info in 29 locales built with Clojure and Htmx https://ift.tt/9H621yS June 3, 2026 at 11:24PM

Show HN: Ideogram 4.0 – open-weight 9.3B text-to-image model https://ift.tt/VTeZnvl

Show HN: Ideogram 4.0 – open-weight 9.3B text-to-image model It's our new text-to-image model: a 9.3B single-stream diffusion transformer trained entirely from scratch. We focused heavily on controllability through structured JSON prompts, with strong text rendering, spatial awareness through bounding box guidance, and color palette control. It has the best text rendering of any open-weight model we've tested so far, and the NF4 quantized checkpoint runs on a single 24GB GPU. For more technical details and examples see our blog post: https://ift.tt/l7zrvLN We will be happy to answer any questions :) https://ift.tt/T5SwePN June 3, 2026 at 11:00PM

Show HN: RePlaya – self-hosted browser session replay with live tailing https://ift.tt/rtnxaq6

Show HN: RePlaya – self-hosted browser session replay with live tailing Hi HN, I'm one of the founders of s2.dev. RePlaya ( https://ift.tt/tHyr3q4 ) is a self-hosted browser session replay tool using rrweb ( https://ift.tt/3mJjgQp ). It occurred to me that a durable stream per session would be a much neater architectural foundation for much of what you'd want from such a tool. As a unique feature, it also made live tailing straightforward because the player can read from the same stream the recorder is appending to. The alternative architecture is likely an ingest firehose which is then indexed, with associated complexity and latency. You'd have to string together multiple data systems like a message queue, a metadata database, and blob storage and/or an OLAP database. Here the only dependency is S2, which has an open source version you can self-host called s2-lite ( https://ift.tt/paHLT7I ). How it works: - one S2 stream per browser session - large rrweb events (like a full snapshot) get framed across multiple binary S2 records and reassembled on read - active sessions are tailed with an S2 read session, and bridged to the browser over SSE - session listing relies on stream names encoding reverse timestamps, as S2 returns a lexicographic order listing - relying on fencing tokens so a stopped session can't be written to again by a late recorder - retention and GC are handled via S2 stream config, so no background job needed Curious to hear from folks on the tool or the stream-per-session model! https://ift.tt/tHyr3q4 June 3, 2026 at 12:40AM

Show HN: Hop – JSX for Rust https://ift.tt/xOIXDkf

Show HN: Hop – JSX for Rust https://hoplang.com June 3, 2026 at 12:08AM

Show HN: I built a way to find and install Claude skills https://ift.tt/9W6onGm

Show HN: I built a way to find and install Claude skills I've been experimenting with ways to increase AI adoption for non-technical people. Basically, all companies are pushing for AI because it's all over the news and they feel left behind but most people have no clue where to start. I think 90% of people (ie non coders) are sufficiently well served by using cowork instead of claude code or something similar. If we can get people from sales, customer support, marketing, etc to collaborate with skills and cowork to form a company brain, I think it's gold. So I think there's opportunity for the community to share skills that work well for 1000s of use cases. However, it's currently quite hard to find good skills and figure out if they're worth it. Gstack has had immense success because of Gary's reach and credibility. Can something like Claudinho.xyz host skills built by the community? What are your thoughts / concerns? https://www.claudinho.xyz/ June 3, 2026 at 12:07AM

Show HN: DropLock – E2EE secret sharing web app with no backend https://ift.tt/Kr2J1u6

Show HN: DropLock – E2EE secret sharing web app with no backend https://ift.tt/mxo9C64 June 2, 2026 at 10:14PM

Show HN: Trumpstonks – every company Trump's named, backtested vs. the S&P https://ift.tt/hC3qYSo

Show HN: Trumpstonks – every company Trump's named, backtested vs. the S&P https://ift.tt/g05xoOD June 2, 2026 at 12:30AM

Show HN: Textile – A desktop app for weaving together bits of text https://ift.tt/U1pwkeZ

Show HN: Textile – A desktop app for weaving together bits of text Hi all, I'm excited to show off Textile, a desktop app I recently built. Textile can combine bits of text using various inputs, such as commands on your computer, the contents of your clipboard, and hard-coded strings that you provide. It lets you carefully build up and modify a dynamic string, step by step, until it's exactly how you need it. The saved steps can then be executed on demand, with the click of a button or using a keyboard shortcut. I built Textile because I was often constructing complicated, dynamic URLs from various sources that all existed on my computer. I got tired of manually switching between different apps, copying and pasting various chunks of text, and assembling them all together somewhere. I've also found Textile to be quite useful as a kind of repository for obscure bits of static text, such as ½ and other fraction characters, when I can't be bothered to remember their built-in keyboard combinations. I also built Textile because I wanted to learn Electron, although I expect there will be some gnashing of teeth about this here. :) I think desktop development is quite interesting, in part because it doesn't require me, the developer, to pay for an API server and database in the cloud. The app itself is both the UI and the "server," and the local drive is effectively the "database." I knows this trades away syncing with the cloud but, on the other hand, there's something nice about knowing that your files are on your drive and not on somebody else's server. I realize that something like Textile may already exist, and may have much more functionality but, again, I wanted to learn. I must say that multi-sequence keyboard shortcuts are hard, and there are cases that don't work right in Textile. I feel vulnerable admitting that my approach has much room for improvement! For what it's worth, I did not use an LLM to write any code for Textile (although I did ask many questions of an LLM, as an alternative to Googling). Textile is open source, free to use, and does not require sign up, email, phone, or other such barriers. Try it and let me know what you think! (Note: I don't have access to hardware running Windows or Linux, so Textile is only available for macOS at the moment.) https://ift.tt/nQByFRx June 2, 2026 at 01:54AM

Show HN: Valdr - Valkey/Redis in safe Rust, passes >99% of Valkey test suite https://ift.tt/XrZMaqx

Show HN: Valdr - Valkey/Redis in safe Rust, passes >99% of Valkey test suite https://ift.tt/fmB1ojT June 1, 2026 at 11:23PM

Show HN: A desktop app for manual QA testing and evidence gathering https://ift.tt/3rvNLeg

Show HN: A desktop app for manual QA testing and evidence gathering https://ift.tt/mR83oY1 June 1, 2026 at 11:47PM