The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Find Hidden Gems on HN
Hey HN. I created this website.<p><a href="https://pj4533.com/hn-overlooked/" rel="nofollow">https://pj4533.com/hn-overlooked/</a><p>It's just a simple web app that discovers overlooked posts on Hacker News. I created it because I was often coming to Hacker News and realizing that I was missing a lot of stuff, and there just didn't seem to be an easy way to surface content that was interesting to me but just didn't bubble up to the top of the page. So I built this.<p>I got the idea a while back, one night when I was recording (you can watch it here, it's pretty funny: <a href="https://youtu.be/FDyDb4sX30w?si=E3rby-DaGWA6gy0R" rel="nofollow">https://youtu.be/FDyDb4sX30w?si=E3rby-DaGWA6gy0R</a> ). But I never really did anything with the idea. So I decided just to make it into a little single-page web app.<p>The Hacker News API is pretty cool because it doesn't require an API key, so you can just vibe code against it super easy. I just loaded up Claude Code and started talking to it. That first night when I was recording, it was just me with this repo, that I call 'thefuture' and I just put everything in there: scripts, whatever. Then i'll have Claude Code use OpenAI to talk to me and I'll just get bored and explore different APIs and see what I can come up with. That's all inside a single repo that Claude Code knows about, and just set it in YOLO mode and just go to town - it's super fun. It's kind of slow though, so that's the only downside. But if you put a script in there for Claude to talk to you, it can be pretty fun just to explore things.<p>This website is just one idea extracted from that one session of messing around with a Claude Code last month. I open sourced it, you can look at the repo here: <a href="https://github.com/pj4533/hn-overlooked" rel="nofollow">https://github.com/pj4533/hn-overlooked</a>
Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown
I got tired of Claude hallucinating Swift APIs. It does a good job at Python and TypeScript, but ask it about SwiftUI and it's basically guessing.<p>The problem? Apple's docs are JavaScript-rendered, so when you paste URLs into AI tools, they just see a blank page. Copy-pasting works but... c'mon.<p>So I built something that converts Apple Developer docs to clean markdown. Just swap developer.apple.com with sosumi.ai in any Apple docs URL and you get AI-readable content.<p>For example:<p>- Before: <a href="https://developer.apple.com/documentation/swift/double" rel="nofollow">https://developer.apple.com/documentation/swift/double</a><p>- After: <a href="https://sosumi.ai/documentation/swift/double" rel="nofollow">https://sosumi.ai/documentation/swift/double</a><p>The site itself is a small Hono app running on Cloudflare Workers. Apple's docs are actually available as structured data, but Apple doesn't make it obvious how to get it. So what this does is map the URLs, fetch the original JSON, and render as Markdown.<p>It also provides an MCP interface that includes a tool to search the Apple developer website, which is helpful.<p>Anyway, please give this a try and let me know what you think!
Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown
I got tired of Claude hallucinating Swift APIs. It does a good job at Python and TypeScript, but ask it about SwiftUI and it's basically guessing.<p>The problem? Apple's docs are JavaScript-rendered, so when you paste URLs into AI tools, they just see a blank page. Copy-pasting works but... c'mon.<p>So I built something that converts Apple Developer docs to clean markdown. Just swap developer.apple.com with sosumi.ai in any Apple docs URL and you get AI-readable content.<p>For example:<p>- Before: <a href="https://developer.apple.com/documentation/swift/double" rel="nofollow">https://developer.apple.com/documentation/swift/double</a><p>- After: <a href="https://sosumi.ai/documentation/swift/double" rel="nofollow">https://sosumi.ai/documentation/swift/double</a><p>The site itself is a small Hono app running on Cloudflare Workers. Apple's docs are actually available as structured data, but Apple doesn't make it obvious how to get it. So what this does is map the URLs, fetch the original JSON, and render as Markdown.<p>It also provides an MCP interface that includes a tool to search the Apple developer website, which is helpful.<p>Anyway, please give this a try and let me know what you think!
Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown
I got tired of Claude hallucinating Swift APIs. It does a good job at Python and TypeScript, but ask it about SwiftUI and it's basically guessing.<p>The problem? Apple's docs are JavaScript-rendered, so when you paste URLs into AI tools, they just see a blank page. Copy-pasting works but... c'mon.<p>So I built something that converts Apple Developer docs to clean markdown. Just swap developer.apple.com with sosumi.ai in any Apple docs URL and you get AI-readable content.<p>For example:<p>- Before: <a href="https://developer.apple.com/documentation/swift/double" rel="nofollow">https://developer.apple.com/documentation/swift/double</a><p>- After: <a href="https://sosumi.ai/documentation/swift/double" rel="nofollow">https://sosumi.ai/documentation/swift/double</a><p>The site itself is a small Hono app running on Cloudflare Workers. Apple's docs are actually available as structured data, but Apple doesn't make it obvious how to get it. So what this does is map the URLs, fetch the original JSON, and render as Markdown.<p>It also provides an MCP interface that includes a tool to search the Apple developer website, which is helpful.<p>Anyway, please give this a try and let me know what you think!
Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown
I got tired of Claude hallucinating Swift APIs. It does a good job at Python and TypeScript, but ask it about SwiftUI and it's basically guessing.<p>The problem? Apple's docs are JavaScript-rendered, so when you paste URLs into AI tools, they just see a blank page. Copy-pasting works but... c'mon.<p>So I built something that converts Apple Developer docs to clean markdown. Just swap developer.apple.com with sosumi.ai in any Apple docs URL and you get AI-readable content.<p>For example:<p>- Before: <a href="https://developer.apple.com/documentation/swift/double" rel="nofollow">https://developer.apple.com/documentation/swift/double</a><p>- After: <a href="https://sosumi.ai/documentation/swift/double" rel="nofollow">https://sosumi.ai/documentation/swift/double</a><p>The site itself is a small Hono app running on Cloudflare Workers. Apple's docs are actually available as structured data, but Apple doesn't make it obvious how to get it. So what this does is map the URLs, fetch the original JSON, and render as Markdown.<p>It also provides an MCP interface that includes a tool to search the Apple developer website, which is helpful.<p>Anyway, please give this a try and let me know what you think!
Show HN: PageIndex – Vectorless RAG
Not all improvements come from adding complexity — sometimes it's about removing it.<p>PageIndex takes a different approach to RAG. Instead of relying on vector databases or artificial chunking, it builds a hierarchical tree structure from documents and uses reasoning-based tree search to locate the most relevant sections. This mirrors how humans approach reading: navigating through sections and context rather than matching embeddings.<p>As a result, the retrieval feels transparent, structured, and explainable. It moves RAG away from approximate "semantic vibes" and toward explicit reasoning about where information lives. That clarity can help teams trust outputs and debug workflows more effectively.<p>The broader implication is that retrieval doesn't need to scale endlessly in vectors to be powerful. By leaning on document structure and reasoning, it reminds us that efficiency and human-like logic can be just as transformative as raw horsepower.
Show HN: A private, flat monthly subscription for open-source LLMs
Hey HN! We've run our privacy-focused open-source inference company for a while now, and we're launching a flat monthly subscription similar to Anthropic's. It should work with Cline, Roo, KiloCode, Aider, etc — any OpenAI-compatible API client should do. The rate limits at every tier are higher than the Claude rate limits, so even if you prefer using Claude it can be a helpful backup for when you're rate limited, for a pretty low price. Let me know if you have any feedback!
Show HN: I built AI that turns 4 hours of financial analysis into 30 seconds
I built Duebase AI to solve a problem I kept running into in fintech - analyzing UK company financial health takes forever.
The process usually goes: download PDFs from Companies House → manually extract data to spreadsheets → calculate ratios → interpret trends. Takes 3-4 hours per company and requires serious financial expertise.
The technical challenge: Companies House filings are messy. Inconsistent formats, complex accounting structures, missing data, and you need to understand UK accounting standards to make sense of it all.
My approach:<p>Parse 15M+ UK company records from Companies House API
Built ML models to extract and normalize financial data from varied filing formats
Created scoring algorithms that weight liquidity, profitability, leverage, and growth trends
Generate 1-5 health scores with explanations in plain English<p>What it does:<p>Instant financial analysis of any UK company (30 seconds vs 4 hours)
Real-time monitoring with alerts for new filings/director changes
Risk detection that catches declining trends early
No financial background needed to understand results<p>The hardest part was handling the data inconsistencies - UK companies file in different formats, use various accounting frameworks, and often have incomplete information. Had to build a lot of data cleaning and normalization logic.
Currently focused on the UK market since I know the regulatory landscape well, but the approach could work for other countries with similar public filing systems.
Link: <a href="https://duebase.com" rel="nofollow">https://duebase.com</a>
Show HN: SwiftAI – open-source library to easily build LLM features on iOS/macOS
We built SwiftAI, an open-source Swift library that lets you use Apple’s on-device LLMs when available (Apple opened access in June), and fall back to a cloud model when they aren’t available — all without duplicating code.<p>SwiftAI gives you:
- A single, model-agnostic API
- An agent/tool loop
- Strongly-typed structured outputs
- Optional chat state<p>Backstory: We started experimenting with Apple’s local models because they’re free (no API calls), private, and work offline. The problem: not all devices support them (older iPhones, Apple Intelligence disabled, low battery, etc.). That meant writing two codepaths — one for local, one for cloud — and scattering branching logic across the app. SwiftAI centralizes that decision. Your feature code stays the same whether you’re on-device or cloud.<p>Example<p><pre><code> import SwiftAI
let llm: any LLM = SystemLLM.ifAvailable ?? OpenaiLLM(model: "gpt-5-mini", apiKey: "<key>")
let response = try await llm.reply(to: "Write a haiku about Hacker News")
print(response.content)
</code></pre>
It's open source — we'd love for you to try it, break it, and help shape the roadmap. Join our discord / slack or email us at root@mit12.dev.<p>Links<p>- GitHub (source, docs): <a href="https://github.com/mi12labs/SwiftAI" rel="nofollow">https://github.com/mi12labs/SwiftAI</a><p>- System Design: <a href="https://github.com/mi12labs/SwiftAI/blob/main/Docs/Proposals/001-llm-api.md" rel="nofollow">https://github.com/mi12labs/SwiftAI/blob/main/Docs/Proposals...</a><p>- Swift Package Index (compat/builds): <a href="https://swiftpackageindex.com/mi12labs/SwiftAI" rel="nofollow">https://swiftpackageindex.com/mi12labs/SwiftAI</a><p>- Discord <a href="https://discord.com/invite/ckfVGE5r" rel="nofollow">https://discord.com/invite/ckfVGE5r</a> and slack <a href="https://mi12swiftai.slack.com/join/shared_invite/zt-3c3lr6dat-jJ8BHBsdWc47o4FDu2CgHQ#/shared-invite/email" rel="nofollow">https://mi12swiftai.slack.com/join/shared_invite/zt-3c3lr6da...</a>
Show HN: SwiftAI – open-source library to easily build LLM features on iOS/macOS
We built SwiftAI, an open-source Swift library that lets you use Apple’s on-device LLMs when available (Apple opened access in June), and fall back to a cloud model when they aren’t available — all without duplicating code.<p>SwiftAI gives you:
- A single, model-agnostic API
- An agent/tool loop
- Strongly-typed structured outputs
- Optional chat state<p>Backstory: We started experimenting with Apple’s local models because they’re free (no API calls), private, and work offline. The problem: not all devices support them (older iPhones, Apple Intelligence disabled, low battery, etc.). That meant writing two codepaths — one for local, one for cloud — and scattering branching logic across the app. SwiftAI centralizes that decision. Your feature code stays the same whether you’re on-device or cloud.<p>Example<p><pre><code> import SwiftAI
let llm: any LLM = SystemLLM.ifAvailable ?? OpenaiLLM(model: "gpt-5-mini", apiKey: "<key>")
let response = try await llm.reply(to: "Write a haiku about Hacker News")
print(response.content)
</code></pre>
It's open source — we'd love for you to try it, break it, and help shape the roadmap. Join our discord / slack or email us at root@mit12.dev.<p>Links<p>- GitHub (source, docs): <a href="https://github.com/mi12labs/SwiftAI" rel="nofollow">https://github.com/mi12labs/SwiftAI</a><p>- System Design: <a href="https://github.com/mi12labs/SwiftAI/blob/main/Docs/Proposals/001-llm-api.md" rel="nofollow">https://github.com/mi12labs/SwiftAI/blob/main/Docs/Proposals...</a><p>- Swift Package Index (compat/builds): <a href="https://swiftpackageindex.com/mi12labs/SwiftAI" rel="nofollow">https://swiftpackageindex.com/mi12labs/SwiftAI</a><p>- Discord <a href="https://discord.com/invite/ckfVGE5r" rel="nofollow">https://discord.com/invite/ckfVGE5r</a> and slack <a href="https://mi12swiftai.slack.com/join/shared_invite/zt-3c3lr6dat-jJ8BHBsdWc47o4FDu2CgHQ#/shared-invite/email" rel="nofollow">https://mi12swiftai.slack.com/join/shared_invite/zt-3c3lr6da...</a>
Show HN: Chat with Nano Banana Directly from WhatsApp
Hey everyone, built this earlier today on my whatsapp no code platform - been going a bit viral between my social groups so thought I'd share with you guys :)
Show HN: Chat with Nano Banana Directly from WhatsApp
Hey everyone, built this earlier today on my whatsapp no code platform - been going a bit viral between my social groups so thought I'd share with you guys :)
Show HN: Regolith – Regex library that prevents ReDoS CVEs in TypeScript
I wanted a safer alternative to RegExp for TypeScript that uses a linear-time engine, so I built Regolith.<p>Why:
Many CVEs happen because TypeScript libraries are vulnerable to Regular Expression Denial of Service attacks. I learned about this problem while doing undergraduate research and found that languages like Rust have built-in protection but languages like JavaScript, TypeScript, and Python do not. This library attempts to mitigate these vulnerabilities for TypeScript and JavaScript.<p>How:
Regolith uses Rust's Regex library under the hood to prevent ReDoS attacks. The Rust Regex library implements a linear-time Regex engine that guarantees linear complexity for execution. A ReDoS attack occurs when a malicious input is provided that causes a normal Regex engine to check for a matching string in too many overlapping configurations. This causes the engine to take an extremely long time to compute the Regex, which could cause latency or downtime for a service. By designing the engine to take at most a linear amount of time, we can prevent these attacks at the library level and have software inherit these safety properties.<p>I'm really fascinated by making programming languages safer and I would love to hear any feedback on how to improve this project. I'll try to answer all questions posted in the comments.<p>Thanks!
- Jake Roggenbuck
Show HN: Smooth – Faster, cheaper browser agent API
Hey there HN! We're Antonio and Luca, and we're excited to introduce Smooth, a state-of-the-art browser agent that is <i>5x faster</i> and <i>7x cheaper</i> than Browser Use (<a href="https://docs.circlemind.co/performance">https://docs.circlemind.co/performance</a>).<p>We built Smooth because existing browser agents were slow, expensive, and unreliable. Even simple tasks could take minutes and cost dollars in API credits.<p>We started as users of Browser Use, but the pain was obvious. So we built something better. Smooth is 5x faster, 7x cheaper, and more reliable. And along the way, we discovered two principles that make agents actually work.<p>(1) Think like the LLM (<a href="https://x.com/karpathy/status/1937902205765607626" rel="nofollow">https://x.com/karpathy/status/1937902205765607626</a>).<p>The most important thing is to put yourself in the shoes of the LLM. This is especially important when designing the context. How you present the problem to the LLM determines whether it succeeds or fails. Imagine playing chess with an LLM. You could represent the board in countless ways - image, markdown, JSON, etc. Which one you choose matters more than any other part of the system. Clean, intuitive context is everything. We call this LLM-Ex.<p>(2) Let them write code (<a href="https://arxiv.org/pdf/2401.07339" rel="nofollow">https://arxiv.org/pdf/2401.07339</a>)<p>Tool calling is limited. If you want agents that can handle complex logic and manipulate objects reliably, you need code. Coding offers a richer, more composable action space. Suddenly, designing for the agent feels more like designing for a human developer, which makes everything simpler.
By applying these two principles religiously, we realized you don't need huge models to get reliable results. Small, efficient models can get you higher reliability while also getting human-speed navigation and a huge cost reduction.<p>How it works:<p>1. Extract: we look at the webpage and extract all relevant elements by looking at the rendered page.<p>2. Filter and Clean: then, we use some simple heuristics to clean up the webpage. If an element is not interactive, e.g. because a banner is covering it, we remove it.<p>3. Recursively separate sections: we use several heuristics to represent the webpage in a way that is both LLM-friendly and as similar as possible to how humans see it.<p>We packaged Smooth in an easy API with instant browser spin-up, custom proxies, persistent sessions, and auto-CAPTCHA solvers. Our goal is to give you this infrastructure so that you can focus on what's important: building great apps for your users.<p>Before we built this, Antonio was at Amazon, Luca was finishing a PhD at Oxford, and we've been obsessed with reliable AI agents for years. Now we know: if you want agents to work reliably, focus on the context.<p>Try it for free at <a href="https://zero.circlemind.co/developer">https://zero.circlemind.co/developer</a><p>Docs are here: <a href="https://docs.circlemind.co">https://docs.circlemind.co</a><p>Demo video: <a href="https://youtu.be/18v65oORixQ" rel="nofollow">https://youtu.be/18v65oORixQ</a><p>We'd love feedback :)
Show HN: FilterQL – A tiny query language for filtering structured data
Hey all, I just released v2.0.0 of FilterQL, a query language and TypeScript library. This version adds support for Operations, which allow you to transform the data after filtering.<p>If you think this would be useful in a project you're working on, give it a try and let me know what you think!
Show HN: FilterQL – A tiny query language for filtering structured data
Hey all, I just released v2.0.0 of FilterQL, a query language and TypeScript library. This version adds support for Operations, which allow you to transform the data after filtering.<p>If you think this would be useful in a project you're working on, give it a try and let me know what you think!
Show HN: FilterQL – A tiny query language for filtering structured data
Hey all, I just released v2.0.0 of FilterQL, a query language and TypeScript library. This version adds support for Operations, which allow you to transform the data after filtering.<p>If you think this would be useful in a project you're working on, give it a try and let me know what you think!
Show HN: Meetup.com and eventribe alternative to small groups
Mobile first open-source RSVP platform. Alternative for meetup.com / eventribe for small companies and groups. If you have a small group and don't want to pay for services you can easily selfhost this solution. Open for improvements and for feedback, ofc.<p>- One-Click Sharing - Each event gets a unique, memorable URL. Share instantly via any platform or messaging app.
- No Hassle, No Sign-Ups - Skip registrations and endless forms. Unlike other event platforms, you create and share instantly — no accounts, no barriers.
- Effortless Simplicity - Designed to be instantly clear and easy. No learning curve — just open, create, and go.
Show HN: Meetup.com and eventribe alternative to small groups
Mobile first open-source RSVP platform. Alternative for meetup.com / eventribe for small companies and groups. If you have a small group and don't want to pay for services you can easily selfhost this solution. Open for improvements and for feedback, ofc.<p>- One-Click Sharing - Each event gets a unique, memorable URL. Share instantly via any platform or messaging app.
- No Hassle, No Sign-Ups - Skip registrations and endless forms. Unlike other event platforms, you create and share instantly — no accounts, no barriers.
- Effortless Simplicity - Designed to be instantly clear and easy. No learning curve — just open, create, and go.
Show HN: Meetup.com and eventribe alternative to small groups
Mobile first open-source RSVP platform. Alternative for meetup.com / eventribe for small companies and groups. If you have a small group and don't want to pay for services you can easily selfhost this solution. Open for improvements and for feedback, ofc.<p>- One-Click Sharing - Each event gets a unique, memorable URL. Share instantly via any platform or messaging app.
- No Hassle, No Sign-Ups - Skip registrations and endless forms. Unlike other event platforms, you create and share instantly — no accounts, no barriers.
- Effortless Simplicity - Designed to be instantly clear and easy. No learning curve — just open, create, and go.