<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: Show HN</title><link>https://news.ycombinator.com/shownew</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 22 Jun 2026 02:01:40 +0000</lastBuildDate><atom:link href="https://hnrss.org/show" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: Woltspace – a lodge for your coding agents]]></title><description><![CDATA[
<p>Hey HN,<p>I built woltspace as a way to interact with my coding agents when I'm away from the computer. It's fully containerized, so you can give them full access inside their sandbox (the lodge).<p>Right now it supports Claude Code. Each session can be controlled via telegram or slack. You can fully access the terminal running the sessions from anywhere thanks to Cloudflare tunnels.<p>Wolts are creatures with their own personality, goals and memory system. Wolts vary in ability, racoons are smartest (opus) while beavers are faster (sonnets). A wolt also manages its own website , shown in a native split pane; terminal on one side, the wolt's live output on the other.<p>A wolt can build full-stack apps which you self-host and access from anywhere thank to tunnels. Most importantly, it all runs from your machine. You host and own everything.<p>It's fully open source: github.com/jerpint/woltspace<p>Looking for feedback, let me know if you find this useful!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48624578">https://news.ycombinator.com/item?id=48624578</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 22 Jun 2026 01:36:03 +0000</pubDate><link>https://www.woltspace.com/</link><dc:creator>jerpint</dc:creator><comments>https://news.ycombinator.com/item?id=48624578</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48624578</guid></item><item><title><![CDATA[Show HN: Baserates.dev, memorize programmer napkin math]]></title><description><![CDATA[
<p>When I began my career in programming I remember reading Jeff Dean's "Latency Numbers Every Programmer Should Know" [1], and getting inspired. Alas, it's been over a decade, and I never fully internalized all the numbers.<p>Until recently. I discovered Simon Eskildsen's talk [2]  and github repo [3] on programmer napkin math. I liked his reasoning, and decided to _actually_ internalize the numbers now.<p>So I made baserates.dev.<p>It's a spaced repetition program that teaches you the napkin math from Simon, enhanced with a few things from Jeff Dean's list. The main changes: I included CPU instructions, like L1 Cache reads. I also included some nooby context, like how to pronounce the character μ, and a reminder on what is bigger: nano seconds, or micro seconds.<p>The app automatically saves your progress, and doesn't require auth. Most of the logic is vibe coded: I fed Claude all the links. I use InstantDB [^4] for the backend, mainly to support guest auth and saving progress. Most of my time spent on the project was just going through and making sure the numbers were right. [^5]<p>Hope you enjoy it!<p>[1]: <a href="https://gist.github.com/jboner/2841832" rel="nofollow">https://gist.github.com/jboner/2841832</a><p>[2]: <a href="https://www.youtube.com/watch?v=IxkSlnrRFqc" rel="nofollow">https://www.youtube.com/watch?v=IxkSlnrRFqc</a><p>[3]: <a href="https://github.com/sirupsen/napkin-math" rel="nofollow">https://github.com/sirupsen/napkin-math</a><p>[4]: Disclaimer: I am the founder of InstantDB<p>[5]: One fun story: I got claude to spin up a bunch of machines on Amazon, to confirm latency numbers for same AZ, cross AZ, cross region requests.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48624232">https://news.ycombinator.com/item?id=48624232</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 22 Jun 2026 00:50:48 +0000</pubDate><link>https://www.baserates.dev/</link><dc:creator>stopachka</dc:creator><comments>https://news.ycombinator.com/item?id=48624232</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48624232</guid></item><item><title><![CDATA[Show HN: I Built an MCP Server in 200 Lines of Go (and Claude Became 10x Useful)]]></title><description><![CDATA[
<p>Article URL: <a href="https://medium.com/dev-genius/i-built-an-mcp-server-in-200-lines-of-go-and-claude-became-10x-more-useful-5352546a48cb">https://medium.com/dev-genius/i-built-an-mcp-server-in-200-lines-of-go-and-claude-became-10x-more-useful-5352546a48cb</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623994">https://news.ycombinator.com/item?id=48623994</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 22 Jun 2026 00:18:58 +0000</pubDate><link>https://medium.com/dev-genius/i-built-an-mcp-server-in-200-lines-of-go-and-claude-became-10x-more-useful-5352546a48cb</link><dc:creator>cheikhshift</dc:creator><comments>https://news.ycombinator.com/item?id=48623994</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623994</guid></item><item><title><![CDATA[Show HN: Wirewright, an experimental symbolic physics environment]]></title><description><![CDATA[
<p>The idea with Wirewright is to treat programs and algorithms as physical mechanisms, as machines or societies of machines inhabiting an immutable symbolic world, and time-step the latter to see what happens. This last part in particular reminds me of cellular automata.<p>Said differently, in Wirewright, programs are modeled as "nouns" or "societies" of interacting "nouns" (think data structures). The world is then subjected to laws of physics -- symbolic physics; which is the only "verb" here (think function). Therefore, in Wirewright, we say that, in a sense, algorithm equals structure and the evolution of structure equals computation. I tend to shorten this to "structure is computation", but this may be incorrect if viewed in isolation.<p>Now, I guess you're wondering what Wirewright actually <i>is</i>. In fact, I see the rules here state that I must tell you what Wirewright is, plainly and clearly. I will try, but beware that at the end of the day, I know as little as you do :^) My hands write, my brains ponder.<p>It's hard for me to say definitively what Wirewright <i>is</i>. Please see the README for several attempts of mine to answer this question. Please see the tutorial(s) if you're interested enough to try and infer that yourself. I'm still not sure the README or the tutorial(s) are answering the exact question, though; I had no feedback yet on most of my work on Wirewright, so any feedback is welcome, other than, I guess, "I don't understand what this is"; this kind of feedback I can generate myself, no offense :^)<p>If there wasn't a public GitHub repo and if I hadn't made a few announcements here and there already, you'd think I'm developing the project in secret. This kind of stuff is not something you ordinarily talk about, you see, especially "in the wild"; or else you'd be quickly labeled eccentric or outright crazy.<p>Anyway. Wirewright is not a framework, not a UI toolkit, not an IDE. It's not a programming language either. I think I'm trying to explore the intersection of different things here, such as cellular automata, term rewriting, symbolic computation, dataflow, etc. I'm also prone to veering off for pages and pages into a genre one could call "folk biology"; biology and especially neurobiology is a huge inspiration for me. Inspiration doesn't mean copying or formal study, of course. In fact, if there are any biologists here, please "shut down" your eyes and ears and all other sensory organs if you decide to explore the depths of the project :^) For me, when I see something interesting in biology, I think, in excitement, "Oh, I want to do that too, I don't care how!"<p>The project has been evolving more or less organically, along with me, so to speak, subsuming a lot of my ideas (but mostly the ideas of others; e.g., Varela, Maturana, Wolfram), and mixing them. I'd say it's a playground of mine which, over the years, has become consistent enough for me not to fear trying to tell the world about it. That is, about two years ago, Wirewright was an amorphous blob I couldn't even describe with analogies. Now I can at least try analogies. All this "symbolic physics" stuff is the product of my most recent work in recognizing where the project actually appears to be heading.<p>Now, as a final disclaimer, please note I'm an amateur in all of the things I'm talking about, from programming to biology to philosophy. So maybe all of this is well-trodden grounds, and I'm coming up with these words and ideas for nothing, and what I'm saying is stupid. Maybe it is. Regardless, I hope at least the synthesis looks interesting to some of you, even if the exact wording and my little philosophy intermissions here and there feel a bit off.<p>Sorry for the long text.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623965">https://news.ycombinator.com/item?id=48623965</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 22 Jun 2026 00:15:08 +0000</pubDate><link>https://github.com/wirewright/wirewright</link><dc:creator>homonoidian</dc:creator><comments>https://news.ycombinator.com/item?id=48623965</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623965</guid></item><item><title><![CDATA[Show HN: Phileas – Local-first memory that remembers you]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/alexajuno/phileas">https://github.com/alexajuno/phileas</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623929">https://news.ycombinator.com/item?id=48623929</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 22 Jun 2026 00:07:18 +0000</pubDate><link>https://github.com/alexajuno/phileas</link><dc:creator>alexajuno</dc:creator><comments>https://news.ycombinator.com/item?id=48623929</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623929</guid></item><item><title><![CDATA[Show HN: TaxLens – free lodging-tax API for hotels, OTAs, and property managers]]></title><description><![CDATA[
<p>Article URL: <a href="https://taxlens.getdynamiq.ai">https://taxlens.getdynamiq.ai</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623803">https://news.ycombinator.com/item?id=48623803</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 21 Jun 2026 23:46:40 +0000</pubDate><link>https://taxlens.getdynamiq.ai</link><dc:creator>vitalii-duk</dc:creator><comments>https://news.ycombinator.com/item?id=48623803</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623803</guid></item><item><title><![CDATA[Show HN: ANMA, boundary contracts for cheaper AI coding agents]]></title><description><![CDATA[
<p>I built ANMA because I noticed that cheaper models would often ignore architecture rules. So I did several benchmarks using "Claude Haiku 4.5" with and without ANMA; without ANMA it ignored the "rules" 13 out of 19 runs, with ANMA, 0 out of 20 runs.<p>What is "ANMA"? 
YAML contracts with CLAUDE.md, hooks, and CI checks<p>What about stronger/expensive models?
They followed the architecture rules.<p>The question is, would cheaper models with stronger rules be the best affordable default for coding?</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623765">https://news.ycombinator.com/item?id=48623765</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Sun, 21 Jun 2026 23:41:02 +0000</pubDate><link>https://github.com/anma-labs/anma</link><dc:creator>nxy</dc:creator><comments>https://news.ycombinator.com/item?id=48623765</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623765</guid></item><item><title><![CDATA[Show HN: AI Colours]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/pilotpirxie/ai-colours">https://github.com/pilotpirxie/ai-colours</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623764">https://news.ycombinator.com/item?id=48623764</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 21 Jun 2026 23:40:55 +0000</pubDate><link>https://github.com/pilotpirxie/ai-colours</link><dc:creator>__natty__</dc:creator><comments>https://news.ycombinator.com/item?id=48623764</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623764</guid></item><item><title><![CDATA[Show HN: PeekAI – Local-first observability for Python AI agents]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/oussamaKH63/peekai">https://github.com/oussamaKH63/peekai</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623745">https://news.ycombinator.com/item?id=48623745</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 21 Jun 2026 23:38:15 +0000</pubDate><link>https://github.com/oussamaKH63/peekai</link><dc:creator>ousskh63</dc:creator><comments>https://news.ycombinator.com/item?id=48623745</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623745</guid></item><item><title><![CDATA[Show HN: Lupen – an itemized, verified receipt for Claude Code and Codex spend]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/momoraul/Lupen">https://github.com/momoraul/Lupen</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623711">https://news.ycombinator.com/item?id=48623711</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 21 Jun 2026 23:32:03 +0000</pubDate><link>https://github.com/momoraul/Lupen</link><dc:creator>momoraul</dc:creator><comments>https://news.ycombinator.com/item?id=48623711</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623711</guid></item><item><title><![CDATA[Show HN: Real-Life Deception Detection Without Uploading Video]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/WhissleAI/lie_detection_binary">https://github.com/WhissleAI/lie_detection_binary</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623405">https://news.ycombinator.com/item?id=48623405</a></p>
<p>Points: 1</p>
<p># Comments: 2</p>
]]></description><pubDate>Sun, 21 Jun 2026 22:51:01 +0000</pubDate><link>https://github.com/WhissleAI/lie_detection_binary</link><dc:creator>ksingla025</dc:creator><comments>https://news.ycombinator.com/item?id=48623405</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623405</guid></item><item><title><![CDATA[Show HN: Fold-logging.nvim – fold logging and debug-print statements in Neovim]]></title><description><![CDATA[
<p>I made this because I often keep debug logs and print statements around while working, but I don’t want them to dominate the file when I’m reading or reviewing code.<p>fold-logging.nvim adds folds for logging/debug-print statements while leaving normal code folds alone. Python is built in for now, and other languages can be added with Treesitter call node types and Lua patterns.<p>It currently supports commands to fold, unfold, toggle, refresh, and list detections in quickfix.<p>I’d be interested in feedback on whether the detection rules are lacking, and which languages would be worth supporting by default.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623250">https://news.ycombinator.com/item?id=48623250</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 21 Jun 2026 22:30:00 +0000</pubDate><link>https://github.com/markosnarinian/fold-logging.nvim</link><dc:creator>markosn</dc:creator><comments>https://news.ycombinator.com/item?id=48623250</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623250</guid></item><item><title><![CDATA[Show HN: Tunr – Expose your local server in 3 seconds]]></title><description><![CDATA[
<p>tunr - open source ngrok / pinggy alternative</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623146">https://news.ycombinator.com/item?id=48623146</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 21 Jun 2026 22:14:03 +0000</pubDate><link>https://github.com/ahmetvural79/tunr</link><dc:creator>ahvural</dc:creator><comments>https://news.ycombinator.com/item?id=48623146</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623146</guid></item><item><title><![CDATA[Show HN: Bifrost Edge: runs on PC of ur organization and routes all AI traffic]]></title><description><![CDATA[
<p>Article URL: <a href="https://docs.getbifrost.ai/edge/overview">https://docs.getbifrost.ai/edge/overview</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623080">https://news.ycombinator.com/item?id=48623080</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Sun, 21 Jun 2026 22:04:55 +0000</pubDate><link>https://docs.getbifrost.ai/edge/overview</link><dc:creator>aanthonymax</dc:creator><comments>https://news.ycombinator.com/item?id=48623080</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623080</guid></item><item><title><![CDATA[Show HN: EGC - MCP server that gives AI coding tools memory across sessions]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/Fmarzochi/EGC">https://github.com/Fmarzochi/EGC</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48623049">https://news.ycombinator.com/item?id=48623049</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 21 Jun 2026 22:01:38 +0000</pubDate><link>https://github.com/Fmarzochi/EGC</link><dc:creator>fmarzochi</dc:creator><comments>https://news.ycombinator.com/item?id=48623049</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48623049</guid></item><item><title><![CDATA[Show HN: Recall – fully-local project memory for Claude Code]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/raiyanyahya/recall">https://github.com/raiyanyahya/recall</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48622590">https://news.ycombinator.com/item?id=48622590</a></p>
<p>Points: 70</p>
<p># Comments: 55</p>
]]></description><pubDate>Sun, 21 Jun 2026 21:05:37 +0000</pubDate><link>https://github.com/raiyanyahya/recall</link><dc:creator>mateenah</dc:creator><comments>https://news.ycombinator.com/item?id=48622590</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48622590</guid></item><item><title><![CDATA[Show HN: Annotate.js – Turn anywebsite into Figma style reviewboard]]></title><description><![CDATA[
<p>MIT licensed and opensource. A simple Javascript plugin which turns any website into a Figma Style collaborative reviewboard. Users could submit their comments and download them as JSON to be shared with original author. No backend required.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48622545">https://news.ycombinator.com/item?id=48622545</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 21 Jun 2026 20:59:45 +0000</pubDate><link>https://reviewjs.github.io/annotate/</link><dc:creator>aagosh</dc:creator><comments>https://news.ycombinator.com/item?id=48622545</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48622545</guid></item><item><title><![CDATA[Show HN: Tot – instant share links for HTML and Markdown files]]></title><description><![CDATA[
<p>Each file is backed by cloudflare artifacts & is backed by git, enabling VCS.<p><a href="https://tot.page/" rel="nofollow">https://tot.page/</a><p>Treat the share model the same way you would an excalidraw live link.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48622133">https://news.ycombinator.com/item?id=48622133</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 21 Jun 2026 20:05:34 +0000</pubDate><link>https://github.com/plannotator/tot</link><dc:creator>ramoz</dc:creator><comments>https://news.ycombinator.com/item?id=48622133</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48622133</guid></item><item><title><![CDATA[Show HN: DebugBrief – turn debugging sessions into reports, no AI]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/harihkk/Debug-Brief">https://github.com/harihkk/Debug-Brief</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48622061">https://news.ycombinator.com/item?id=48622061</a></p>
<p>Points: 6</p>
<p># Comments: 1</p>
]]></description><pubDate>Sun, 21 Jun 2026 19:57:54 +0000</pubDate><link>https://github.com/harihkk/Debug-Brief</link><dc:creator>itshkrishna</dc:creator><comments>https://news.ycombinator.com/item?id=48622061</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48622061</guid></item><item><title><![CDATA[SHOW HN: I built a social profile for vibecoders to share & store their projects]]></title><description><![CDATA[
<p>Article URL: <a href="https://kritive.com">https://kritive.com</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48621959">https://news.ycombinator.com/item?id=48621959</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Sun, 21 Jun 2026 19:44:20 +0000</pubDate><link>https://kritive.com</link><dc:creator>sonOfHades</dc:creator><comments>https://news.ycombinator.com/item?id=48621959</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48621959</guid></item></channel></rss>