Show HN: TownSquare, a tiny presence layer for websites https://bit.ly/4uUlS1f

Show HN: TownSquare, a tiny presence layer for websites https://bit.ly/4afYDHr https://bit.ly/4v86qil https://bit.ly/3QXTu0d June 20, 2026 at 12:55PM

Show HN: Autonomy – Self-Harness/Self-Directed AI Agent Core Under Development https://bit.ly/4aZAoxo

Show HN: Autonomy – Self-Harness/Self-Directed AI Agent Core Under Development https://bit.ly/4w4oElF June 20, 2026 at 07:31AM

Show HN: Pytest-tia – run only the tests your Git diff affects, with receipts https://bit.ly/4uPo22b

Show HN: Pytest-tia – run only the tests your Git diff affects, with receipts https://bit.ly/4uTgv2l June 20, 2026 at 07:14AM

Show HN: Rundown - Niche Intelligence for YouTube Creators https://bit.ly/4vpe8FF

Show HN: Rundown - Niche Intelligence for YouTube Creators https://bit.ly/4vS8Z8E June 20, 2026 at 04:47AM

Show HN: Let agents send/receive SMS using your old Android phone https://bit.ly/4vhhJ8t

Show HN: Let agents send/receive SMS using your old Android phone While playing with agents I realised it might be quite handy if they could get access to OTP codes. And while at it, why not give them ability to send the SMS as well. Twillio is expensive and annoying to set up for my taste. I vibe coded simple Android app that can read/send SMS and simple relay server that acts as MCP for agents. Works surprisingly well and my old android phone from a drawer is doing something useful again. Feel free to use it if you find it useful. I put it just to a $5 vps. If it's crashed, you should be able to spin up your own instance on your own VPS just in a few minutes. https://bit.ly/4vhhJoZ June 19, 2026 at 10:06PM

Show HN: BeamWeaver – LangChain/DeepAgents-style agents and workflows for Elixir https://bit.ly/4oBItyb

Show HN: BeamWeaver – LangChain/DeepAgents-style agents and workflows for Elixir Hi HN, We build agents in Elixir. We kept running into the same issue and found there is no observability for agentic systems. We decided to take the best aspects of LangChain, LangGraph, and DeepAgents and put them into Elixir. BeamWeaver comes with an OTP-native design and: - agents and tool calling - graph workflows - checkpoints and resumable execution - memory stores - retries, fallbacks, interrupts, and human review - typed streaming events - provider adapters for OpenAI, Anthropic, Google Gemini, xAI, and Moonshot/Kimi - fake/replay models for deterministic tests We're also building observability on top of it through WeaveScope, which we'll release very soon. BeamWeaver gives Elixir teams the tools needed to build advanced agentic systems without pushing the hard parts into Python services. https://bit.ly/43Gggwv June 19, 2026 at 03:06AM

Show HN: Talos – Open-source WASM interpreter for Lean https://bit.ly/44nzPty

Show HN: Talos – Open-source WASM interpreter for Lean At Cajal (YC W26) we’re excited to share Talos ( https://bit.ly/4uIKTw4 ), an open source framework for formal verification of WebAssembly modules in Lean. AI is now writing tons of the code that gets pushed to production. As code generation gets cheaper, verification becomes the bottleneck. We believe in a future where every piece of software comes with a mathematical proof that it does what its author intended - in doing so, eliminating many classes of exploits. Talos is part of the foundation for that. Talos provides a Wasm interpreter optimized for reasoning at the binary level, together with a weakest-precondition calculus layer for proving properties about programs. Because we reason directly about WebAssembly, any language with a Wasm backend is in scope: Rust, C++, Go, C, Swift, Kotlin, Zig, C#, and many more. To make this possible, we use Lean: a programming language and theorem prover that lets you both write software and mathematically prove that it's correct - all in one system. That's what lets Talos double as both an executable interpreter and the formal object Lean reasons about. Lean also integrates with modern AI proving tools, discharging goals automatically via both proof search and direct evaluation. To see Talos in action check out a proof for Stein's GCD algorithm, implemented in the popular Rust crate num-integer: https://bit.ly/4vWWSaz... . Our roadmap: - Full Wasm coverage by first passing the official W3C testsuite, then later verifying against SpecTec (formal Wasm spec) - Arbitrary crate verification - any Rust crate that compiles to Wasm should be in scope - Building our proof library codelib, to make verifying increasingly complex programs tractable We would love to hear the community’s feedback on Talos and comments on the state of formal verification right now. Contributions are also welcome! https://bit.ly/4uIKTw4 June 18, 2026 at 02:10PM

Show HN: Crawlie – Free open-source SEO audit tool for humans and agents https://bit.ly/4vkbyR4

Show HN: Crawlie – Free open-source SEO audit tool for humans and agents With AI, it's faster than ever to ship a marketing site... but most of what gets generated is slop that was never built to be found. Plus the tools meant to catch that fall short: most SEO auditors cost money, don't play nicely with your agents, or tell you what's wrong without telling you how to actually rank for SEO and GEO (Generative Engine Optimization: being cited by AI search like ChatGPT, Perplexity, and Google AI Overviews). crawlie fixes that! It's 100% free, it's local-first, it's agent-native (MCP baked in!), and every issue it finds comes with why it matters and how to fix it. https://bit.ly/4vrQt7C June 18, 2026 at 11:54PM

Show HN: Cowork/Codex DOCX plugin. Uses 2x fewer tokens than the docx skill https://bit.ly/4vT84Vz

Show HN: Cowork/Codex DOCX plugin. Uses 2x fewer tokens than the docx skill Hi HNers, I'd like to share our DOCX plugin for Cowork and Codex. It uses 2-5x fewer tokens compared to the traditional docx skill because it doesn't write any code nor execute python/node script. It is also much more reliable. Our DOCX plugin converts docx<->html bidirectionally. This means AI only operates on HTML. AI is excellent and very efficient when it comes to HTML. Most libraries (if not all) support docx->html, but none supports html->docx. This is what is novel about our approach. Here's the demo: https://bit.ly/44e6mlR... We've been using it in-house for redlining legal documents, and we love it. If you redline docx files, please give it a try: https://bit.ly/4ecMPrW... https://bit.ly/4uMFBzQ June 18, 2026 at 01:49AM

Show HN: Reyn – local-first AI that journals and recalls your work https://bit.ly/4vb9vie

Show HN: Reyn – local-first AI that journals and recalls your work Hey HN, I built Reyn - which I like to describe as "granola but for everything". You're probably thinking another screen capture AI tool (which is true). Same as always, the biggest question that comes up is privacy, so I'll talk about that first 1. raw screen data is never stored in the cloud 2. user controlled filters are granular to the point that you're able to configure specific apps, windows, websites, or even keywords to be discarded immediately (once again never leaving your mac) and never captured down the pipeline I personally built it because I find it useful and always had the problem of organizing my day (not note taking or task management), as well as sharing context on things that just happened to go undocumented throughout my day. As I was building it I decided to go even further and see if I could collect useful insights and find room for improvements in my day to day workflow. This led to the current version of Reyn and its differentiating factor being the fact that it has a proactive layer. Most tools in this space are reactive - you ask, they retrieve. Reyn surfaces insights on its own and sends a daily recap of what you worked on, what's still open, and what deserves attention. The journal feature also lets you search across basically anything you've done on your Mac. The proactive insights work by first having you configure what your ideal workday looks like — whether that's hours worked or the type of work being done. We have a few broad categories that tasks fall under, with more customization coming. Current integrations: Obsidian (available now, improvements in progress) Gmail, calendar, web search via a floating window with some agentic functionality Notion (coming soon) BYOK for LLM API requests (on the roadmap) ... and more It's still early, but the journal and insights features are the strongest parts right now. Would love some feedback especially on the privacy model. My personal take - I think with enough safeguards in place, the data aggregated about your work is fully in your control. A lot of these data sources already store your data. If you're using Notion, Claude, or just browsing a website, that data is already being stored somewhere. Reyn is just aggregating it and putting it to work for you. Happy to answer any questions about how it works usereyn.com (public beta) https://bit.ly/3S6u4hk June 17, 2026 at 11:31PM

Show HN: Day-ahead river discharge forecasting using USGS and ERA5 data https://bit.ly/4oxdYJJ

Show HN: Day-ahead river discharge forecasting using USGS and ERA5 data https://bit.ly/4eBb4PE June 17, 2026 at 08:25AM

Show HN: Easy text to social media cards platform https://bit.ly/4vjxv2O

Show HN: Easy text to social media cards platform Includes text to card conversion, visual editing, variations and integration for posting directly from the editor. https://bit.ly/4vrbMWw June 17, 2026 at 12:47AM

Show HN: Numax - a portable runtime for distributed apps https://bit.ly/43G77E4

Show HN: Numax - a portable runtime for distributed apps Hi, over the past few months I've been working on this project: Numax is a small Rust runtime that does three things: it runs WebAssembly modules in a sandbox, has a built-in local key-value store, and syncs everything across nodes with CRDTs and gossip. Basically, you write a wasm module, run it on two machines, and they converge (I hope !). It's a decentralized system... I hope someone finds it interesting! There's a whitepaper I've put a lot into, and I think the code isn't bad either! I believe there's still room in this world for software that's fun and well made, and while building Numax I had a great time! I love Numax and I love software. Thanks to anyone who'll spend a bit of their time even just to open the repo and take a look! https://bit.ly/4eLVYYy June 16, 2026 at 11:25PM

Show HN: Tamper-evident audit trail for AI coding agent activity https://bit.ly/4uHCklb

Show HN: Tamper-evident audit trail for AI coding agent activity We released what I've been working in the last few months: an Openclaw plugin that ecords every session, tool invocation, and prompt exchange into a local SQLite database with SHA-256 hash chain integrity, so you can verify that no events were altered or deleted after the fact. https://bit.ly/3SHD0K4 June 16, 2026 at 12:01AM

Show HN: Wtdb – give every Git worktree its own database https://bit.ly/43D2Tx3

Show HN: Wtdb – give every Git worktree its own database I run a lot of agentic coding sessions in parallel, each in its own git worktree. Every worktree points at the same local Postgres though, so the moment one branch runs a migration it changes the schema out from under the others. I'd end up with agents tripping over each other, or me babysitting which branch "owned" the DB at any given moment. I made this to fix it. I hope you might find it helpful too. https://bit.ly/43Bt1Z7 June 15, 2026 at 12:35AM

Show HN: Coding agent with algebraic memory (VSA) instead of RAG https://bit.ly/4vaAnyO

Show HN: Coding agent with algebraic memory (VSA) instead of RAG https://bit.ly/43x7KzV June 15, 2026 at 12:44AM

Show HN: Is Fable 5 available? (it is not) https://bit.ly/4eMcVkL

Show HN: Is Fable 5 available? (it is not) https://bit.ly/4oq4506 June 14, 2026 at 11:33PM

Show HN: I run a vision model on every screenshot, locally, on a 4GB GPU https://bit.ly/3Sm41CI

Show HN: I run a vision model on every screenshot, locally, on a 4GB GPU https://bit.ly/4e9N0UZ June 14, 2026 at 12:12AM

Show HN: Slopsome – a VRAM fit calculator and tok/s database for local LLMs https://bit.ly/3S6rTKA

Show HN: Slopsome – a VRAM fit calculator and tok/s database for local LLMs https://bit.ly/4fL7YuA June 13, 2026 at 08:44PM

Show HN: Lightweight Task queue on Erlang/OTP, SQLite-backed, no overengineering https://bit.ly/49X84eM

Show HN: Lightweight Task queue on Erlang/OTP, SQLite-backed, no overengineering Setting up Kafka or such enterprise oriented software with their clusters or dedicated servers is heavy and bothering enough that most small teams or indie hackers skip it entirely and making compromise to use in-memory queues. I wanted something in between: a persistent queue that is simple to run (one binary, which makes one sqlite db), gets real fault isolation and crash recovery due to Elixir, easy to inspect (open ezra.db in any SQLite browser and see every task), and requires no new client library - it speaks the Redis Streams wire protocol, so any Redis client in any language just works out of the box. Very short demo video: [ https://www.youtube.com/watch?v=MLYyD3DVWmE ] https://bit.ly/4eJGwv9 June 10, 2026 at 02:45PM

Show HN: LLMRender, a 10kb Markdown+LaTeX renderer for React https://bit.ly/4xx2E4u

Show HN: LLMRender, a 10kb Markdown+LaTeX renderer for React I've been using the popular React Markdown renderers with Katex and Prism.js for rendering my Markdown and LaTeX, but was tired of having to bundle 300kb+ of min+gzip JS only for this (1.2MB+ of plain JS!). So I created a small Markdown renderer that does it all in a tiny package. I added a small playground to the homepage, please feel free to try it and let me know what you think! It's not perfect, it's definitely not "correct" in that I'm using Regex internally instead of a proper AST parser, but for my usecase and the majority of Markdown out there, this works perfectly fine (cue the StackOverflow post [1]). It's also conservative for this reason; no HTML by default, parsing wrong content produces escaped HTML entities instead of XSS. [1] https://bit.ly/4xrJ1dY https://bit.ly/4eGTRFm June 13, 2026 at 05:11AM

Show HN: Lead Qualifier – Get leads qualified in minutes https://bit.ly/4vKNWow

Show HN: Lead Qualifier – Get leads qualified in minutes https://bit.ly/4eizvky June 13, 2026 at 03:36AM

Show HN: Putt.day a daily mini golf game https://bit.ly/3S4HTgg

Show HN: Putt.day a daily mini golf game https://bit.ly/3S10Mk9 June 12, 2026 at 11:56PM

Show HN: Manob: A social media plaform without algorithm, ads, or data-tracking https://bit.ly/4oqKyN9

Show HN: Manob: A social media plaform without algorithm, ads, or data-tracking I built Manob because I kept running into the same frustration with every major social media platform. A feed I couldn't control, content that I couldn't trust, and also a sense that I (my user data) am the product, not the user. I talked with people about these thoughts and concerns, and added my personal observation. I built this instead: - Chronological feed only. No ranking, no algorithmic shuffling. You follow people, you see all posts from all users, or choose to see posts from friends, pages you follow, and groups you are part of. - Built-in fact-checking and bias detection across text, images, and video. With Human-in-the-loop & AI combined in the process, AI detects, analyzes, and moderates posts, and every contested moderation decision is reviewed by a human against a published set of principles (not just personal judgment only). - Per chat AES-256 encryption. We designed a way that currently, if a chat is attacked and compromised, it doesn't have any effect on other chats or the platform in any way - this is constantly being improved, and security is my top priority. - No ads currently. Your data is never sold or shared (minor data is stored, all in encrypted strings) - Child safety filtering is built into the content layer - Pseudonymous mode for speaking about sensitive topics - A built-in news feed The moderation system is designed to evolve; it is more like a constitution than a rulebook. The principles are fixed but can be amended as the platform grows and severe cases emerge. The goal is to detect as accurately as possible, systematically, over claims of neutrality and move on. I'm still working on figuring out monetization. I'm thinking of contextual ads that work based on the viewing page's contents, and not on your behavioral profile. Additionally, other features like the job board and commercial tools are also an option. None of this is live at the moment, and tbh, I'm still figuring it out. The platform is currently LIVE with a small early community of active users. I'm building this solo. I'm happy to answer your questions/feedback/suggestions... https://bit.ly/3QccXtS June 12, 2026 at 06:06AM

Show HN: Dont lose your friends, use a Kadoodle to plan your next event https://bit.ly/4vJRuYe

Show HN: Dont lose your friends, use a Kadoodle to plan your next event https://bit.ly/4v9HmZ0 June 12, 2026 at 06:03AM

Show HN: A Claude Code statusline that shows live World Cup scores https://bit.ly/4xpZM9l

Show HN: A Claude Code statusline that shows live World Cup scores Hey HN, I built this a side project because I'm a soccer fan that has been vibing and tokenmaxxing with Claude Code maybe too much. So, the World Cup is here and it was the perfect excuse to build and ship something from 0 to 1. Enter Claudinho, a CLI and MCP that puts World Cup scores on your terminal. No signup, no account, no data collection. The components are: - status line in Claude Code with live scores rendered always from cache, no polling. - userPromptSubmit hook so Claude gets score updates mid vibecoding session, only during a live match. - A standard MCP server and a CLI with options to see groups, standings, matches and market signal info. More details in Github. Let me know what you think, I hope you find it fun and useful! Not affiliated with FIFA or Anthropic. https://bit.ly/4fHn1W8 June 12, 2026 at 03:31AM

Show HN: Deploy personal apps with your agent via Buildy https://bit.ly/3Sma0Yd

Show HN: Deploy personal apps with your agent via Buildy Hi HN, I'm one of the creators of Buildy. More and more people seem to be building personal software, including myself. But I keep re-implementing the same things: authentication, database setup, creating an API/MCP server to integrate them into my AI agent. We built Buildy for LLM generated personal apps. How it works: Buildy exposes an API and MCP that the agent can call with an ES module plus an optional UI and CSS. We run the ES module on a workerd isolate with a persistent KV store, then release your UI to a live URL only accessible by you. Not only that, but your app APIs are exposed securely over both HTTP and MCP so your agent can call them and use the apps you build (log a meal, create a workout plan, update a note, etc.) If your AI chat client supports MCP Apps, we can also render your app inline via an iframe. This works today with ChatGPT and Claude. Here is an app I built to track my nutrition: https://bit.ly/4v8A9Zd... ← You can actually claim this app and remix it with your own agent. To ship a completely new app, drop this prompt into your agent: Read https://bit.ly/3RTTAX3 then help me create my first app. Or check out our landing page ( https://bit.ly/4up5WUl ) to use our ChatGPT app or connect it to Claude via MCP. I personally use apps I built every day. I'd love to hear from other people building and using their own personal apps. Would love feedback from people building and using their own personal apps. https://bit.ly/4up5WUl June 12, 2026 at 01:08AM

Show HN: Catalyst Maze: biotech trading game https://bit.ly/4upkHXd

Show HN: Catalyst Maze: biotech trading game I'm trying to learn about portfolio management, and built this biotech trading game to help understand basic portfolio management concepts: ie, how do you improve investing performance by things other than getting an 'edge' on an asset? I have a biotech investing background, but still learning portfolio management. So if there are some basic errors in this, please tell me! https://bit.ly/43rxWMk June 11, 2026 at 01:21AM

Show HN: Jailbreak this model to get 3B tokens https://bit.ly/4elH8a5

Show HN: Jailbreak this model to get 3B tokens https://bit.ly/4ebMKTZ June 11, 2026 at 12:47AM

Show HN: Magenta Real-Time Music Generation Locally on iPhone, Without the GPU https://bit.ly/4xqKwsU

Show HN: Magenta Real-Time Music Generation Locally on iPhone, Without the GPU Last Thursday, Deepmind released Magenta Realtime 2 , an open source music generation model. They said it could run on Mac, but not iPhone. As a v̵i̵b̵e̵ ̵c̵o̵d̵i̵n̵g̵ ̵a̵d̵d̵i̵c̵t̵ agentic AI maxxi and person who has melted iPhones before (link at bottom), I took that as a personal challenge and made it my weekend project. On Saturday, I got it to run for 10min straight on an iPhone 12 Pro from 2020 without melting the phone or - shockingly - touching the GPU. How? I chopped the model up into 5 pieces and set them each to run on different parts of Apple's system on a chip (SoC). My past experience taught me that if you can actually leverage it, the iPhone's NPU is incredibly powerful, and power efficient. If you're doing sustained real-time generation for long periods of time on a device without a fan, you gotta use the neural engine or else you will melt the device. See: https://bit.ly/4ot5K5m The Apple Neural Engine has a ton of constraints, the main one being that it only accepts fixed shape inputs, and only supports some architectures -- which is why I chopped the model up into pieces. But it works! And I wrote zero lines of code by hand. Back when I was running VC-backed companies, I would have needed a small team of grumpy greybeard engineers to do this and it would have taken 2-6 weeks. Now I can feed my own nerd fetish and do this stuff myself. Next up: I'm building an iPhone app that ties into your heart rate, movement data, location etc to generate a real-time soundtrack to you life. What a time to be alive! update: Demo video of it running on my iPhone 15 Pro: https://bit.ly/3RY7Gqh https://bit.ly/49OqDls June 10, 2026 at 11:22PM

Show HN: KnowledgeMCP – Turn any docs into an MCP endpoint (0 LLM at query time) https://bit.ly/440eE0y

Show HN: KnowledgeMCP – Turn any docs into an MCP endpoint (0 LLM at query time) https://bit.ly/3QAgd2d June 10, 2026 at 01:36AM

Show HN: Live audit log of every command, file, network connection by Claude https://bit.ly/4uvhF3Y

Show HN: Live audit log of every command, file, network connection by Claude https://bit.ly/4xqLiGn June 9, 2026 at 11:26PM

Show HN: DaysLeft – a bio-age clock that shows a range, not a death date https://bit.ly/4xwT0yK

Show HN: DaysLeft – a bio-age clock that shows a range, not a death date https://bit.ly/49MCW1s June 9, 2026 at 01:52AM

Show HN: Ustps (UDP Speedy Transmission Protocol Secure) and USSH https://bit.ly/49JTG9F

Show HN: Ustps (UDP Speedy Transmission Protocol Secure) and USSH Hi HN, Over the last few days I've been building USTPS (UDP Speedy Transmission Protocol Secure), an experimental encrypted transport protocol built on top of UDP. The primary goal of USTPS is low-latency video streaming. A server can take a video source and expose it through a USTPS endpoint, while Linux and Android (Termux) clients receive the stream and expose it locally to applications such as VLC, mpv, and FFmpeg. Although streaming is the main focus, USTPS is not limited to media delivery. It can also be used for other reliable encrypted UDP-based applications, which is why I built USSH on top of it. Some of the main design differences compared to TCP-based transports are: - USTPS is reliable but unordered. - If packet N is lost, later packets can still be accepted and processed immediately. - Missing packets are recovered through selective retransmission. - Ordering is handled by the application layer when needed. This means the transport layer itself does not introduce Head-of-Line Blocking. The tradeoff is that applications which require ordering must implement reordering themselves. I consider this a reasonable tradeoff because it avoids forcing every application to pay the cost of transport-level ordering. For media player compatibility, the default USTPS client creates a local TCP endpoint at 127.0.0.1:1238. The client maintains a small reordering buffer (350 ms by default) to give retransmissions time to arrive before forwarding data to the local TCP stream. This allows existing software such as VLC, mpv, and FFmpeg to work without modification. USTPS currently provides: - Reliable delivery using ACKs and selective retransmissions - X25519 key exchange - AEAD encryption (AES-GCM and ChaCha20-Poly1305) - Optional unordered live output mode - Stream position metadata - Multi-client support - Local TCP compatibility output - No congestion control (currently intentional) While developing USTPS, I also built USSH, an SSH-like remote shell running entirely over USTPS. USSH uses the same unordered transport underneath, but the client reconstructs and orders terminal data before presenting it to the user. This prevents terminal corruption while still allowing the transport layer itself to remain unordered. USSH includes: - Interactive terminal sessions - PTY support - Password authentication - Host key verification (TOFU) - End-to-end encrypted communication through USTPS I'm currently using USSH from my Android phone through Termux to manage my VPS. The project is very young (less than a week old) and is primarily experimental and educational. I'm interested in feedback from people working on transport protocols, streaming systems, SSH implementations, QUIC, SCTP, and networking software. USTP-Secure: https://bit.ly/4oqDT5F USSH: https://bit.ly/43VGmeV Internet-Drafts: USTPS Draft: https://bit.ly/3QvVHzI USSH Draft: https://bit.ly/4v8C7IX Questions, criticism, and suggestions are welcome. https://bit.ly/4oqDT5F June 9, 2026 at 12:00AM

Show HN: NoSuggest – Watch YouTube without the recommendation algorithm https://bit.ly/4vCZ475

Show HN: NoSuggest – Watch YouTube without the recommendation algorithm NoSuggest is a quiet act of resistance against YouTube algorithms always trying to pull you into a loop of unlimited videos in turn into unlimited screen time. With unending side cards of videos, auto-play, what's next suggestions, YouTube shorts and notifications, users will be doom scrolling for many hours in a day. I faced the same problem. Acknowledging that, not all content in YouTube is bad. There are educational videos, genuine news contents without political bias which is very hard to find outside YouTube and many other good relaxing, entertainment stuff. NoSuggest lets you only follow the YouTube channels you like and removes all types of recommendation YouTube has. So you don't waste time on watching things which you never wanted to watch anyways. UI is very simple. You add your favourite channels in "Channels" tab and latest 5 videos per channel excluding shorts would appear in "Feed" tab. "Search" tab is to search for specific videos to watch and "Saved" tab is to bookmark any video you want to watch later. Intention of NoSuggest is to provide whatever is necessary to extract whats good from YouTube all inside NoSuggest and leave out bad parts. NoSuggest works in any devices. Install it as an app (PWA) in android and iPhone, or simply open in browser in laptops. No sign-in, no account creation or no card details. NoSuggest won't even ask your name. Total privacy for the users. Parents can add the channels and save some educational videos and lock it with the pin for kids mode. Kids won't be able access unwanted additive contents inside NoSuggest. Completely free, no string attached. Source available in Github through NoSuggest website. I would love genuine feedback. Thank you very much for your attention on this matter. https://bit.ly/43hVGCv June 3, 2026 at 10:14PM

Show HN: An mkv player that uses WASM to render you videos https://bit.ly/4xf5Cdu

Show HN: An mkv player that uses WASM to render you videos hello HN i want to share this wasm experience i built for a universal mkv player on the web using wasm to ship a lean decoder only ffmpeg build, thus way codecs unsupported by the browser can be played I wonder if this holds any value to anyone anymore https://bit.ly/4xeq8uJ June 8, 2026 at 12:57AM

Show HN I scraped 743 large employers' careers pages to find their ATS https://bit.ly/4e7kmTb

Show HN I scraped 743 large employers' careers pages to find their ATS https://bit.ly/4xaI2id June 7, 2026 at 06:45PM

Show HN: Aquifer – an MCP runtime for spiky agent tool traffic https://bit.ly/4ofYFoy

Show HN: Aquifer – an MCP runtime for spiky agent tool traffic https://bit.ly/4okQYgY June 7, 2026 at 12:08AM

Show HN: Keybench – Scriptable, extensible performance tool for key value stores https://bit.ly/4e9uVoP

Show HN: Keybench – Scriptable, extensible performance tool for key value stores I've been working with storage engines for quite a while and really there was no similar tool to sysbench and or HammerDB for key-value storage engines. Thus I introduce a POC called keybench. I hope you check it out, and do give it a run to drive your favorite engine. Cheers! https://bit.ly/4uj92sY June 7, 2026 at 12:06AM

Show HN: Documenting an Obscure Japanese Wii Game – and-Kensaku https://bit.ly/4uTHsUr

Show HN: Documenting an Obscure Japanese Wii Game – and-Kensaku I have been using Claude for the past couple of days this week to document and modify the TR2 game file format for an obscure Japanese-exclusive Wii game called And-Kensaku, or 安藤ケンサク. And-Kensaku is a game related to Googling. There are a few game modes, but the most famous one asks you a question and gives you two answer options, and you win if you choose the most popular Google search. I have been able to do the following: 1. disable signature checks on the files, and 2. allow edits to the Phrases.tr2 file, making it possible to modify the content of the aforementioned game mode. I wanted to go on this little adventure because reverse-engineering file formats is an extremely difficult (at least for me) and time-consuming task, and I wondered how well Claude would do at it. Right now, not everything about this game is documented, but I would like to fully document it and maybe release an English patch. https://bit.ly/4foIhjb June 6, 2026 at 01:48AM

Show HN: Omni – Local-first multimodal file search on macOS https://bit.ly/4vCfHjf

Show HN: Omni – Local-first multimodal file search on macOS Finally made something I've always wanted, using the model we built. • SOTA omni embedding model, fully local, indexes text, PDF, image, audio, and video • Swift-native app UI + mlx-swift-transformer core. No Python. • Tested on M3 Pro 18G / M3 Ultra 512G / M4 Pro 48G. All work fine. • HTTP server exposes search to local agents like OpenClaw & Hermes − Indexing still feels slow even on the latest M3 Ultra, ranging from 10K tps to 300 tps depending on file type − Fans go crazy, high power draw while indexing − Search is near-instant. Multimodal relevance is sometimes arguable, but the idea is recall (the agentic LLM takes the results and refines for the final answer), so maybe that's fine https://bit.ly/4x8eFNv June 6, 2026 at 12:20AM

Show HN: I nerfed our coding agents on purpose https://bit.ly/4agEscl

Show HN: I nerfed our coding agents on purpose Tl;dr: I trained a classifier to route to the least expensive model and reasoning depth to complete the request. Coupling that with additional automated token efficiency techniques has yielded 3x usage for the same spend. For anyone interested in trying it themselves: https://bit.ly/4vwwAeT Various teammates and I switched over to Codex from Claude Code recently. We still bounce between the tools, but Codex’s speed and steerability coupled with performance gains were hard to ignore. One of the downsides was that the per token pricing kicked in way sooner. This is happening across the board, but we felt it in Codex more acutely. We’re a startup filled with people who work around the clock and are obsessed with building — naturally our daily bill alone was striking. Luckily we’re going after a big mission and speed matters significantly more than marginal token spend on the edges. Still, it got us thinking about how it was ludicrous that while our product has a side effect of decreasing token spend and speeding up agentic workflows by many orders of magnitude, we were using these top tier models for all types of internal coding tasks without any of those optimizations. The waste felt pretty ridiculous — the most glaring culprit was that we were seemingly using the max intelligence model on max reasoning for every task even when the task clearly didn’t require it. As a company who spends a lot of time on cached intelligence, it was also easy for us to see how there was plenty of other low hanging fruit as well. So, on a recent weekend, I quickly built a tool to optimize our usage. At its core is a very fast classifier that classifies your requests to the least intelligence required for the task and includes some nice token optimizations on top. The result is roughly the same quality for multiples lower token spend. But even more exciting for us, is that the properly bin packed intelligence and reasoning levels meant our speed also went up considerably. This wasn’t negligible. We’ve observed up to 3x savings and hours per day per person in saved time that we would have otherwise been waiting on tool turns and coding agent responses. For us, that means improved engineering velocity and significantly higher usage for the same spend. It also means more usage before getting throttled. As I told friends about this, they also wanted to start using it to maximize the usage they could get out of their coding agent plans. There are now engineers across many of the most cutting edge AI companies using this tool to optimize their token utilization in this way. Not just to save money, but to maximize output. Turns out that the best way to avoid getting nerfed by Claude is to intentionally nerf yourself selectively. We decided to release it for the rest of the builder community to use as well. You can now turn on Nerfguard for yourself and start getting more usage today. June 6, 2026 at 12:19AM

Show HN: I embedded 685M public texts in 32 minutes (on 8x A100, Rust, TensorRT) https://bit.ly/3Q8vzuu

Show HN: I embedded 685M public texts in 32 minutes (on 8x A100, Rust, TensorRT) Quick note on how it works and how I've done my batch embedding engine IgniteMS. The whole thing runs as one process using Rust, reading input, tokenizing, packing batches, keeping the queue full. TensorRT handles inference. Python is only as a wrapper. I built it this way because when you use more than couple of GPUs, the GPUs stop being the problem. CPU cannot feed them fast enough. One A100 can go through batches faster than Python can tokenize and feed, so the GPU just sits there idle waiting for work. Most of my time went into optimizing this. At 8 GPUs that was basically the entire challenge. On cost. I ran the big 2B messages job on a spot p4d instance (8x A100 40GB). After filtering and dedupping I got 685M raw texts. With my new engine the whole production run finishes in about half an hour. Previously I used on-demand for these jobs, now switched to spots. If AWS reclaims the box, I just rerun it. It's roughly $7 for half-an-hour run. And at least right now spots are easier to get than on-demand. Open warning: it's batch only and NVIDIA only. You can use it both as a docker image and native. I used some optimizations for my production run. With default settings you can expect to see ~250K msg/sec if you run the benchmark script on your p4d box. https://bit.ly/43cKXcq... v1.1.0 added TensorRT 11 and 60 models, 23 tested on 1x and 4x A100. Happy to share details. https://bit.ly/4ufYz1o June 4, 2026 at 04:23PM

Show HN: ControllerTest-test gamepads,stick drift and polling rate by browser https://bit.ly/43grSGm

Show HN: ControllerTest-test gamepads,stick drift and polling rate by browser https://bit.ly/4uRpAt9 June 5, 2026 at 01:21AM

Show HN: A native port of Skate 3 for Windows & Linux via static recompilation https://bit.ly/4e61W5i

Show HN: A native port of Skate 3 for Windows & Linux via static recompilation https://bit.ly/43cyghN June 4, 2026 at 10:57PM

Show HN: Uruky (EU-based Kagi alternative) now has Image Search and URL Rewrites https://bit.ly/4uKBO6U

Show HN: Uruky (EU-based Kagi alternative) now has Image Search and URL Rewrites You can get a 2h free trial by solving a proof-of-work captcha when topping up your account for the first time. If you'd like to learn more, an independent interview was posted a couple of weeks ago [1], and the FAQ [2] has a lot of information as well. For the source code sharing, we've talked with lawyers and are inclined to no longer require the NDA/NCC for privacy reasons shared with us before (signing requires identification), but instead use a source-available permissive license that doesn't allow competition, like PolyForm Shield [3] (we do still have about 6 months before finalising a decision, here). This does come with a lot more risks for us (it's harder to track down if someone publishes the code or uses it against the license), but given we've already passed 100 monthly active accounts, we're feeling more confident it's an acceptable risk. The plan is to give logged in accounts (who are 12 months old or more) a way to download a ZIP of the current code base that's in the server. Obviously there's no easy way to prove that's the case, but we're open to ideas/suggestions if someone here has them. [1]: https://bit.ly/4uPl7XY... [2]: https://bit.ly/3PYXBJ2 [3]: https://bit.ly/49GOrrd https://bit.ly/4uRIZKP June 4, 2026 at 09:56AM

Show HN: I've hooked up 2D LiDARs to Raspberry Pi, wrote Python library lds2d https://bit.ly/3RP9emn

Show HN: I've hooked up 2D LiDARs to Raspberry Pi, wrote Python library lds2d Try it in 60 seconds - no hardware needed. It supports 23+ LiDAR models including LDROBOT, YDLIDAR, RPLIDAR, 3irobotix, Neato, Xiaomi, Camsense and Hitachi-LG. https://bit.ly/4x9V8Mr June 4, 2026 at 08:10AM

Show HN: an AI that settles small couple arguments https://bit.ly/4vt1MvN

Show HN: an AI that settles small couple arguments Nisrine and I have been working in the same company for many years (she's Head of Product, I am CPTO) and we have done great things for our employer(s) all along. But we always wondered if we could launch our own app – after all, we know the process of it all, we just "never had the time". The idea started from a random conversation, after Nisrine told me a personal story about she had a stupid little fight with her partner, and after 3 or 4 back-and-forths on each side, she decided she was right. Of course, he decided HE was. But he was not sure, so he asked chatGPT... And lost :) We were making fun of him but then we thought, wait: everybody fights for stupid little things. It would be great if someone impartial, neutral, with no bias, could move the needle in one direction. Not render a verdict like in a Roman Forum but just shows you where (both of) you are right or wrong, and then makes the person who is more in the wrong apologise. Yeah, an AI :) Why apologise? One, because it's the best way to bring back peace to any relationship. Two, because it's hard to let go, put your ego on the side and accept that, "yeah, it's not worth fighting or sulking, sorry". And three... because it's so cool to see the other one bow and lose the argument :) Come on, don't pretend this is not thrilling to win an argument! So we built this app, called Piece (sounds like Peace, it's the peace of offering to bring back peace – the logo is an olive branch). The app comes with different tones: witty, theatrical, sarcastic and counsellor (if you want to go deeper in the analysis). The principle is very simple: you record yourself, your partner records their version, you get an analysis of each side's good and weak points, then a verdict. The app stores everything locally, no personal data shared anywhere (except the ephemeral transcript). And the two partners need to use one phone only: that brings them closer already. And from there, you can imagine all the features you want: dashboard with analytics (who has the biggest ego? how many times do you fight?), sharing on social media for "funny" humiliation, karma points, music generation of your fights etc. This app does not replace the couple therapy apps, of course. We are more malicious, this is more about a gamified experience for the day to day arguments. While building the app (Claude + Claude Design, app is in Flutter if you're interested), we were amazed by how many hilarious sentences the AI engine came up with. We were not expecting something that smart, to be honest, and that was what we liked about this side project: every test was a laugh! – ok, maybe not when Nisrine introduced regressions in the code: she argues that she did not but we asked Piece, and I won... We had good feedback from regular users so we recently decided to launch for a bigger public. The app is on the iOS and Android stores (look for "Piece, relationships"), works in English and French for now. Free to start, we'll surely implement credits when we grow our audience. Get it from here: https://bit.ly/3S3ti4p Happy to expand on any of this here if you are interested https://bit.ly/4o53eSu June 4, 2026 at 02:16AM

Show HN: Bio Glyph – Turn Your Face into a One-Line Drawing https://bit.ly/4ohLbsn

Show HN: Bio Glyph – Turn Your Face into a One-Line Drawing https://bit.ly/4xdd6hm June 4, 2026 at 01:18AM

Show HN: I reverse-engineered the world maps of Test Drive III (1990 DOS game) https://bit.ly/3SimNuD

Show HN: I reverse-engineered the world maps of Test Drive III (1990 DOS game) https://bit.ly/4dZ96rY May 31, 2026 at 10:45AM

Show HN: AI-Powered PDF to Markdown Converter https://bit.ly/4e3DG3G

Show HN: AI-Powered PDF to Markdown Converter Turn complex PDFs into clean Markdown that people can review and AI tools can use. https://bit.ly/4e3DGkc June 3, 2026 at 03:56AM

Show HN: A crowdsourced map of surveillance camera's based on OSM https://bit.ly/4dL2O0b

Show HN: A crowdsourced map of surveillance camera's based on OSM https://bit.ly/4o4bUsl June 3, 2026 at 02:21AM

Show HN: Paseo – Beautiful open-source coding agent interface https://bit.ly/4x6FxNA

Show HN: Paseo – Beautiful open-source coding agent interface Repo: https://bit.ly/40WjrP9 Homepage: https://bit.ly/4ta6vkO Discord: https://bit.ly/4c7IHrZ https://bit.ly/40WjrP9 June 2, 2026 at 11:34PM

Show HN: Going from 1+1=2 to Quantum Mechanics https://bit.ly/3RUCdVN

Show HN: Going from 1+1=2 to Quantum Mechanics https://bit.ly/4u5B4In June 1, 2026 at 11:27PM

Show HN: NoSleepAgent – keep your MacBook awake until your agents finish https://bit.ly/437Tiy8

Show HN: NoSleepAgent – keep your MacBook awake until your agents finish https://bit.ly/43t0rt3 June 2, 2026 at 12:23AM

Show HN: DepsGuard – one command to harden NPM/pnpm/yarn/bun/uv configs https://bit.ly/3POC85x

Show HN: DepsGuard – one command to harden NPM/pnpm/yarn/bun/uv configs I kept seeing every npm/pnpm/yarn/bun/uv supply chain post end with the same advice (set a minimum release age, turn off install scripts), and while I know cooldowns are "controversial", they do work. But even if you convince people that they should set cooldowns, it seems many don't end up following through, not sure why, maybe because it means hand-editing five config files in five formats with five different time units, or perhaps the "it won't happen to me" syndrome (or "I'll do it later, it seems complicated" where it's actually very simple). So I created a tool that checks what you have set and fixes it for you. I looked for an existing one first and couldn't find it. It started as a small weekend project and turned into a small research project on the nuances of cooldowns across package managers. Not a proof of P vs NP, but a small convenience that can save you and your loved ones from the next supply chain attack. I've raised this in a couple of HN threads since ( https://bit.ly/4wXqIgl and https://bit.ly/4udvqUG ) but never actually did a Show HN for the tool itself. If you know how to edit your ~/.npmrc, which settings apply to npm vs pnpm, and which one wants minutes vs days vs seconds, you probably don't need this. But if you vibe code and just want a one click fix (or you have a PhD in CS from Stanford, ex-FAANG, started 3 YC companies, now work at Anthropic, and still just want a one click fix), read on. DepsGuard is a single Rust binary, no runtime deps, MIT. Run depsguard and it scans your user-level and repo-level configs, shows a table of what is and isn't set, you pick what to change, hit d for the diff, and apply. It writes a timestamped backup first and depsguard restore rolls it back. depsguard scan is read-only if you just want the report. The settings are the simple ones that work: min-release-age / minimumReleaseAge (npm, pnpm, yarn, bun, and uv all name it differently and use days vs minutes vs seconds, which is half of why doing this by hand is annoying), ignore-scripts, and on newer pnpm block-exotic-subdeps, trust-policy: no-downgrade, and strict-dep-builds. It also handles Renovate and Dependabot cooldowns. The whole thing is a bet on timing. The malicious @bitwarden/cli 2026.4.0 was up ~19 hours and got 334 installs. axios was pulled in ~3h, ua-parser-js in hours, node-ipc in days. A 7-day gate means your installer never resolves any of those, they're gone before the window even opens. It does nothing for the slow ones (event-stream sat 2+ months), and it's not SCA, it won't scan your existing lockfile for known CVEs, that's a different layer. Disclosure: I'm a co-founder and CTO at Arnica (a commercial appsec startup) and built this because putting the same recommendations on each blog post felt like yelling at the clouds. It's free and MIT, no account, no telemetry. I'm also not the only one who had the idea (didn't know at the time), cooldowns.dev does the cooldown part across more ecosystems with a shell helper and is worth a look. DepsGuard covers fewer ecosystems but adds the other settings and the diff/backup/restore flow. If you want to try it: cargo install depsguard, or brew/apt/winget/scoop, all in the README. https://bit.ly/4udvrrI (full settings table and FAQ at depsguard.com) Is this an overkill that could have been a shell script? Probably yes (but I wanted windows support, why not). Did it save someone from a supply chain attack? Also probably yes. Do I know personally someone that without it wouldn't have bothered changing their settings after repeatedly asking, but eventually did it when I gave them depsguard? Absolutely yes. https://bit.ly/4udvrrI June 1, 2026 at 05:58PM

Show HN: Postbase – 100% open source Alternative to Firebase and Supabase [video] https://bit.ly/4u9NNKh

Show HN: Postbase – 100% open source Alternative to Firebase and Supabase [video] Postbase – 100% Opensource Alternative to Firebase and Supabase https://www.youtube.com/watch?v=St_kJZXZ_nE June 1, 2026 at 11:17AM

Show HN: Having fun making mini static site apps https://bit.ly/3PWB7It

Show HN: Having fun making mini static site apps I've been having a blast making multiple mini apps that run in the browser. I've been trying to see how far I can go without having a backend and relying on other services. I wrote these for fun and wanted to know what folks think. https://bit.ly/49w2u2K June 1, 2026 at 06:02AM