Show HN: I use AI to send myself personalized weekly recaps from my saved links https://ift.tt/LaxzFkQ

Show HN: I use AI to send myself personalized weekly recaps from my saved links Sharing something that I’ve been working on: I made a save-later app for all my bookmarks. I save links throughout the week and, every Sunday morning, the app sends me a personalized recap with: -patterns and themes that connect my week to my broader interests -a nudge toward links I saved but never revisited -one reflective question to help me decide what else might be worth exploring I was inspired by older read-later apps like Instapaper. I wanted to make something minimalist, so it’s just a simple feed of your links (with tags and annotations linked to each link) and it is set up to ingest all kinds of content, not just text. I also did want it to be bloated as the full-fat AI stuff you see recently. So this is a simpler and more proactive take on the concept of a bookmarking app. Imagine if Pocket and Spotify Wrapped had a baby. I also personally enjoy using the chat to find links across subjects and sources with context, like “Show me the 5 links on travel i’ve returned to the most” or “all recipes with porcini mushrooms” or “show me everything on Topic X i’ve made the most notes on.” I’ve posted about this on HN before, always had great feedback. Happy to answer any questions. (I’m not technical, I'm a writer/ filmmaker.) https://tryeyeball.com/ July 31, 2025 at 04:38AM

Show HN: State of the Art Open-source alternative to ChatGPT Agents for browsing https://ift.tt/HgMKN5C

Show HN: State of the Art Open-source alternative to ChatGPT Agents for browsing Hey HN, We are Winston, Edward, and James, and we built Meka Agent, an open-source framework that lets vision-based LLMs execute tasks directly on a computer, just like a person would. Backstory: In the last few months, we've been building computer-use agents that have been used by various teams for QA testing, but realized that the underlying browsing frameworks aren't quite good enough yet. As such, we've been working on a browsing agent. We achieved 72.7% on WebArena compared to the previous state of the art set by OpenAI's new ChatGPT agent at 65.4%. You can read more about it here: https://ift.tt/cgDrHpW . Today, we are open sourcing Meka, our state of the art agent, to allow anyone to build their own powerful, vision-based agents from scratch. We provide the groundwork for the hard parts, so you don't have to: * True vision-based control: Meka doesn't just read HTML. It looks at the screen, identifies interactive elements, and decides where to click, type, and scroll. * Full computer access: It's not sandboxed in a browser. Meka operates with OS-level controls, allowing it to handle system dialogues, file uploads, and other interactions that browser-only automation tools can't. * Extensible by design: We've made it easy to plug in your own LLMs and computer providers. * State-of-the-art performance: 72.7% on WebArena Our goal is to enable developers to create repeatable, robust tasks on any computer just by prompting an agent, without worrying about the implementation details. We’d love to get your feedback on how this tool could fit into your automation workflows. Try it out and let us know what you think. You can find the repo on GitHub and get started quickly with our hosted platform, https://ift.tt/f69pnVH . Thanks, Winston, Edward, and James https://ift.tt/XF2dwTS July 30, 2025 at 07:41PM

Show HN: Docucod – Automatic documentation for any codebase https://ift.tt/d1jSYXt

Show HN: TanStack DB – Reactive DB with Differential Dataflow for TanStack Query https://ift.tt/uPUZIaT

Show HN: TanStack DB – Reactive DB with Differential Dataflow for TanStack Query Hi HN, Kyle, Sam and the TanStack team here. We’ve been working on TanStack DB, an embedded, reactive client database for TanStack Query, and are proud to announce today that with the 0.1 release that it's now in BETA! TanStack DB plugs into your existing TanStack Query useQuery calls and uses Differential Dataflow to incrementally recompute only what changed, so updates stay sub-millisecond even with 100k rows. You get live queries, optimistic updates with automatic rollback, and streaming joins — all in the client! TanStack DB works with REST, GraphQL, WebSockets, and shines with sync engines like ElectricSQL or Firebase, letting you load large, normalized collections once and stream real-time changes into the client without manual bookkeeping. It sits on top of queryClient so you can adopt it incrementally, one route at a time. - Intro post: https://ift.tt/e9v48NZ... - Local-first sync via Electric: https://ift.tt/2hvz8m5... - Web starter with TanStack Start: https://ift.tt/tm84noV... - Mobile starter with Expo: https://ift.tt/tm84noV... - Project website and docs: https://tanstack.com/db - GitHub repo: https://ift.tt/qyUgsKh Try it out and let us know what you think! https://ift.tt/8Z5PbFL July 29, 2025 at 11:18PM

Show HN: I built a deep email validation library in Kotlin https://ift.tt/6i7Rylq

Show HN: I built a deep email validation library in Kotlin Show HN: I built a deep email validation library to learn Kotlin Hey HN, I wanted a real-world project to properly learn Kotlin (coroutines, DSLs, etc.) and decided to tackle a problem I've found surprisingly underserved: comprehensive email validation. Most solutions stop at regex, but that doesn't prevent sign-ups from user@notarealdomain.com or disposable email services. So, I built a library that performs a series of deeper checks. I just tagged the v1.0.0 release because the API is now stable and I think it's ready for feedback from the community. It validates an email in layers: 1. Syntax: A robust check that's more reliable than a typical regex. 2. Domain Registrability: Checks the domain against the Public Suffix List to ensure it's on a real TLD. 3. MX Records: A DNS query to see if the domain is actually configured to receive email. 4. Disposable Services: Checks against a list of known temporary/throwaway email providers. 5. SMTP Connection (Optional): A live check to see if the mailbox actually exists. This is off by default since port 25 is often blocked, but can be enabled via a proxy. One of my main goals was to build something that would be useful on both the server and on a client like an Android app. This led to a couple of key design decisions: - It's built with coroutines for non-blocking, concurrent I/O. - It has a full offline mode. You can disable all network checks and run it using bundled datasets for things like syntax and disposable domain checks, which is great for providing instant, client-side feedback. The configuration is done through a simple Kotlin DSL. The project is MIT licensed. I'm posting this to get your thoughts on the approach, the architecture, or any Kotlin idioms I might have missed. How do you all typically handle this problem beyond regex? GitHub: https://ift.tt/ku46KW1 https://ift.tt/ku46KW1 July 29, 2025 at 11:40PM

Show HN: Maia Chess – Human-like chess AI for playing, learning, and more https://ift.tt/Dt7mkOh

Show HN: Maia Chess – Human-like chess AI for playing, learning, and more We're thrilled to announce that www.maiachess.com is now in open beta, meaning everyone can access it! Maia is the most human-like chess AI, and is an ongoing research project at the University of Toronto developing fun, useful, and novel human-AI collaboration in chess. Please give it a try and let us know what you think. We're still rapidly improving and iterating on it. * Play Maia-2: Play the (updated) most human-like chess engine, tailored to your skill level * Analyze your games: See how you (or the pros!) stack up with both Maia’s human-based predictions and classic Stockfish evaluation * Try Maia-powered puzzles: Tactics puzzles curated and analyzed through Maia’s unique lens * Openings drill: Brand new! Select openings, play through them against Maia, and get instant, personalized feedback * Hand & Brain: Play this fun team variant where you play with Maia as a human-AI team * Bot-or-not: A chess Turing Test: can you spot the bot in a real human-vs-bot game? * Leaderboards: See how you rank in each mode, and challenge yourself to climb higher We’d love your feedback: what works, what doesn’t, what’s missing, or what would make the platform more valuable for you. Join our Discord to chat with us and other users ( https://ift.tt/g6zLPbq ). If you're interested in our research behind Maia, you can check out these papers: Aligning Superhuman AI with Human Behavior: Chess as a Model System , KDD 2020 Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess , NeurIPS 2021 Learning Models of Individual Behavior in Chess , KDD 2022 Designing Skill-Compatible AI: Methodologies and Frameworks in Chess , ICLR 2024 Maia-2: A Unified Model for Human-AI Alignment in Chess , NeurIPS 2024 Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess , under review https://ift.tt/1obNeZT July 29, 2025 at 10:58PM

Show HN: Mock Interviews for Software Engineers https://ift.tt/7Nr6Gk5

Show HN: Mock Interviews for Software Engineers https://ift.tt/bG5awcB July 29, 2025 at 12:21AM