Saturday, October 31, 2026

Friday, October 30, 2026

Thursday, October 29, 2026

Show HN: I built a map of billboards and banners in Poland (gpy.pl) https://ift.tt/btnuRUJ

Show HN: I built a map of billboards and banners in Poland (gpy.pl) https://gpy.pl/ October 29, 2026 at 01:24AM

Show HN: Measuring how much of an AI-assisted design is yours https://ift.tt/ujM1dqO

Show HN: Measuring how much of an AI-assisted design is yours https://ift.tt/m2tf4Cs October 29, 2026 at 12:11AM

Show HN: OpenTaxRate – open-source US sales tax rates by street address https://ift.tt/LItv3D2

Show HN: OpenTaxRate – open-source US sales tax rates by street address I built this because I tried many sales tax APIs and the problems were: a) the rates were a black box with no source attached b) lookups resolved by ZIP code. ZIP codes are postal routes, not tax jurisdictions. Stripe's Tax team wrote a good post on this [1]: two houses in Drexel, MO share a city, a ZIP, and nearly a house number, but sit in different counties with different rates. If your lookup key is the ZIP, you are wrong on those addresses, even when the rate table is accurate. OpenTaxRate resolves the street address instead: - SST member states (24): the quarterly rate + boundary files, street ranges and ZIP+4, not just the rate tables - Non-SST states: a custom adapter for each state, using its DOR's own published tables and boundary files (TX Comptroller, FL DR-15DSS, ALDOR, IDOR, NY Pub 718, California via CDTFA's lookup, etc) - Census TIGER for geometry I tried with multiple open source geocoders you can self-host: Nominatim, Photon and Pelias, as well as proprietary ones (HERE, Geocodio, Mapbox, Google). Proprietary ones have higher accuracy, ~99.3% correct vs. 97.1% with just open source. For comparison: Avalara AvaTax 99.6%, TaxJar 98.2%. Public benchmark set are in the repo and at opentaxrate.com/benchmarks. Rates are just one part of sales tax, but also there's a ton of work in maintaining it as rules change. It doesn't handle exemptions, holidays, and caps. It returns the rate, plus the state's own location and jurisdiction codes for the address, resolved to the address, with its official source attached. MIT licensed, you can self-host with Postgres + PostGIS. [1]: https://ift.tt/6EkJKlB... https://ift.tt/kAzIRBx October 28, 2026 at 11:10PM

Wednesday, October 28, 2026

Tuesday, October 27, 2026

Show HN: Glider 4.0 Unofficial Web Edition (Mac game port) https://ift.tt/CeJdVOP

Show HN: Glider 4.0 Unofficial Web Edition (Mac game port) https://ift.tt/lBAO0i1 https://ift.tt/RuSgqTz... https://dbohdan.github.io/glider/ October 26, 2026 at 04:48AM

Show HN: Termcraft – 2D terminal survival with multiplayer support https://ift.tt/cPnfI8g

Show HN: Termcraft – 2D terminal survival with multiplayer support Earlier this year, I started developing Termcraft, a terminal-based 2D survival game written in Rust. Since its first release more than half a year ago, I've added multiplayer support, so you can now host a game and play with friends (or colleagues during a meeting?); Up to 8 players. I've also substantially improved the visuals, lighting, physics, and overall gameplay. A friend and I ended up spending the entire weekend playing through the game from start to finish. The progression takes you from gathering wood and building a shelter to crafting equipment, exploring caves, finding diamonds, crossing the Nether, and fighting the Ender Dragon. There are villages, farming, collaborative building, PvP, and player chat along the way. It's open source under the AGPL-3.0 license, with downloadable builds for Linux, macOS, and Windows. Gameplay demo video: https://youtu.be/nn37_15dLFM Installation and controls: https://pagel-s.github.io/termcraft/ It's not perfect, but I'd love to hear your feedback and experiences with the game. Contributions are also more than welcome! https://ift.tt/nAy4EJ5 October 27, 2026 at 12:13AM

Show HN: RPI Pico (RP2040) PIO Emulator Package for Go https://ift.tt/QnIGz8e

Show HN: RPI Pico (RP2040) PIO Emulator Package for Go I have been developing a bus communication protocol for a while using the Raspberry Pi Pico (RP2040)'s programmable IO (PIO) hardware (basically- 8 tiny processors that run assembly programs to manipulate GPIO pins) and I needed some way of testing my programs, as the real hardware is undebuggable. Unfortunately, none of the existing emulators I could find supported connecting multiple RP2040s together, and they each had a few different missing bits of functionality, so I decided to make my own! My emulator supports running multiple RP2040s electrically connected together, and emulates the whole of their PIO blocks (all 8 processors each), along with all of the more niche inter-processor interactions and GPIO functionality I could possibly find in the datasheet. I built it as a Go package so that it can be used inside of other programs; I intend on using it myself inside a test suite against my in-development protocol. I've spent quite a long time checking and double-checking most of the logic so it is as complete and accurate as I can make it, but if you spot anything amiss, I'd really appreciate the feedback. Thanks for checking it out! Hope it can be useful to other RP2040 users. https://ift.tt/IweONuM October 26, 2026 at 10:59PM

Monday, October 26, 2026

Show HN: ReVault – new secure archive format https://ift.tt/CJTd6cm

Show HN: ReVault – new secure archive format reVault is a new, secure-by-default archive format called a lockbox, designed to be simple to use. I've been working on reVault for about 2 years. It was originally written in Dart, but with the improvements in AI, I decided to port it to Rust using AI. It's now in beta, so I'm looking for feedback, particularly around the different language bindings. A lockbox is encrypted, signed and compressed by default. Each can be disabled selectively. - Hybrid post-quantum or passphrase encryption, including metadata. - Zstd compression. - Pure Rust libraries wherever possible. We intend to phase out remaining C code as alternatives become available. The project has been scanned using OpenAI's Daybreak cyber security tools. The manual is a work in progress: https://ift.tt/kC6QUl0 reVault supports Linux, macOS and Windows, x64 and arm64, plus Wasm. The core is Rust, with bindings for C/C++, Java, Dart, Python, Ruby, JS/TypeScript, Go, C#, Kotlin, Lua, PHP and Swift. Within a lockbox you can store: - Files, directories, permissions and symlinks. - Variables. - Forms. Variables, forms and the lockbox itself can have descriptions. reVault uses a portable vault (just another lockbox with structured content) to hold your keys, contacts' keys, lockbox aliases and form definitions. It ties into your platform's secure store, so logging into your desktop unlocks your vault. You don't have to enter a passphrase every time you access a lockbox. You can disable this. There are lots of shortcuts. Creating a lockbox stores an alias in your vault, based on its filename or a name you choose: lbx create /some/path/mybox.lbox lbx mybox open --duration 1h lbx mybox var set KEY VALUE Set a default lockbox and you can leave its name out: lbx session default mybox lbx var get KEY You can mirror a directory tree into a lockbox and update it when the directory changes: lbx store.lbox mirrors project create --from ./project --to /projects/project lbx store.lbox mirrors update The API lets you read, write and seek within files without extracting them to the filesystem. Each lockbox has a table of contents, so extracting a single file from a multi-gigabyte lockbox is fast. Recovery Updates are transactional, with automatic rollback for failed updates. The format is designed for recovery: content is stored in pages, allowing unaffected content to be recovered if part of a lockbox is corrupted. Sharing An encrypted lockbox is more useful if you can share it. reVault has an open-source keyserver for exchanging public keys, with validation through a second trusted channel. It's still experimental. OnePub has donated a server to run a single keyserver. If you're interested in donating resources, I'd like to bring up a second redundant server. It's pure Rust, uses under 100 MB RSS and supports rate limits. To publish your default profile's public key: lbx vault profiles email you@example.com lbx vault profiles publish Give the publish code to your contact. They can import your key: lbx vault contacts receive Display your profile's fingerprint and exchange it through a second trusted channel: lbx vault profiles fingerprint Repeat the process in the opposite direction to get their key. Once you have it, grant them access to your default lockbox: lbx access grant alice You can then email the encrypted lockbox to Alice. To install the CLI and get started: cargo install revault_cli lbx vault init lbx completion install Completion installation detects your shell. To diagnose issues: lbx doctor The language bindings are published to their respective package repositories. I'm looking for constructive criticism of the project on its own merits, particularly the APIs and language bindings. I'm not interested in a debate about using AI. October 25, 2026 at 07:31AM

Sunday, October 25, 2026

Show HN: Steal My Bitcoin https://ift.tt/lpk62Rj

Show HN: Steal My Bitcoin Made this because I'm curious if anyone out there has figured out how to actually use this PHP RCE we spent the last few days panicking over. Have fun! https://ift.tt/z2thYr1 October 25, 2026 at 02:00AM

Show HN: Duls – A bit of du, a bit of ls. Best of both https://ift.tt/Y4C9zDV

Show HN: Duls – A bit of du, a bit of ls. Best of both https://ift.tt/OPxglEF October 25, 2026 at 01:44AM

Show HN: A phone lock I can't undo on impulse because I never learn the code https://ift.tt/5qIyseM

Show HN: A phone lock I can't undo on impulse because I never learn the code https://ift.tt/9CLKY8n October 24, 2026 at 07:52PM

Show HN: Agentsh – A Decentralized, Scalable Multiagent Harness https://ift.tt/rowHtfG

Show HN: Agentsh – A Decentralized, Scalable Multiagent Harness https://ift.tt/gmeubhK October 24, 2026 at 11:49PM

Saturday, October 24, 2026

Show HN: I made a professional audio time-stretcher in Go https://ift.tt/jGHcymM

Show HN: I made a professional audio time-stretcher in Go https://ift.tt/UZAghYB October 24, 2026 at 12:48AM

Show HN: ZapFast, a native WhatsApp client with voice and video calls on Linux https://ift.tt/naQ1UVS

Show HN: ZapFast, a native WhatsApp client with voice and video calls on Linux https://zapfast.rocks/ October 23, 2026 at 11:25PM

Friday, October 23, 2026

Show HN: Light captured – An interractive workshop on photography https://ift.tt/Ag3yjdZ

Show HN: Light captured – An interractive workshop on photography https://ift.tt/mrhpzlH October 22, 2026 at 11:09PM

Thursday, October 22, 2026

Show HN: Overdesigned Simple Solitaire https://ift.tt/uLZCJ1x

Show HN: Overdesigned Simple Solitaire I got irritated by the maximalism and lack of aesthetics present in modern software when trying to find a nice solitaire. A solitaire does not need a score, levels - and most of all it does not need to download anything, have user log in or do anything else except maintain game state. So since software comes automatically nowadays, I decided as a weekend project to create the last solitaire I'll ever need. The application is built on Rust so I can compile it to native. But it runs just as well as web app! I geeked out completely on design (it may look like "default" but that's the point) to create as non-intruding yet aesthetically pleasing experience as I could. I might have accidentally put in a complete card design system with a content pipeline (maybe I'll do default blackjack next) - but as a player you only see the one pack of cards. Anyway, hope someone here appreciates the minimalistic aesthetics. The game state is saved in the url so if you want to save a nice game you can do it by copypasting the link. The game engine is versioned so if I ever change the engine or state schema there will be support for the current version as well. There _is_ a novelty. If you click the "teach" button it shows all the available free moves as arrows. Hope this is fun for someone! https://ift.tt/UNxq1Ee October 22, 2026 at 02:15AM

Show HN: I built ESP32-S3 LED tubes for live coding https://ift.tt/tF7EoJk

Show HN: I built ESP32-S3 LED tubes for live coding https://ift.tt/itZ1U52 October 22, 2026 at 12:25AM

Your Holiday Wardrobe, Muni-Style

Your Holiday Wardrobe, Muni-Style
By Melissa Culross

Our 2026 Muni Holiday Sweater is here! And we’ve got sizes available for the whole family. The holidays are right around the corner, and you’ll be able to count on at least two things this year. First, Muni will get you wherever you need to go all season long. And second, you can dress festively to impress with the 2026 Muni Holiday Sweater. The holiday season means something different for everyone. For us, it’s a time to celebrate San Francisco and more than a century of Muni service. Our new sweater is part of that celebration. Images of Muni and San Francisco adorn this year’s sweater. A...



Published 2026-10-21T00:00:00Z
https://ift.tt/vyLBpCI

Wednesday, October 21, 2026

Overnight Maintenance Puts Shine on Muni’s T Third Corridor

Overnight Maintenance Puts Shine on Muni’s T Third Corridor
By Eric Harding

Muni’s Track Maintenance staff is power washing boarding platforms along the T Third corridor this fall as part of a new overnight maintenance program. While the city sleeps, the streets take on a quiet calmness. Meanwhile, Muni’s Track Maintenance team is wide awake. You may not see them, but their work benefits your ride. Building on the success of Fix It! Weekends this summer, we have developed a proactive maintenance program for the T Third focused on corridor upkeep and reliability. Overnight maintenance work we’re doing along the line includes: • Regular inspecting and cleaning •...



Published 2026-10-20T00:00:00Z
https://ift.tt/1MB7iNW

Show HN: qrsticks https://ift.tt/nAa0O4c

Show HN: qrsticks https://qrsticks.greg.technology/ October 21, 2026 at 01:05AM

Show HN: Rouler – Steer Windows traffic per app or IP across multiple interfaces https://ift.tt/2LRracf

Show HN: Rouler – Steer Windows traffic per app or IP across multiple interfaces Hi HN, Rouler is "rules for your routes". It allows you to steer network traffic across multiple network interfaces on Windows. For example: - Run Tailscale, Mullvad and OpenVPN official clients simultaneously. - Use Rouler to send Slack via the OpenVPN connection, Chrome + an IP range via Tailscale and a torrent client via Mullvad. Rouler is VPN agnostic, so you can "split-tunnel" with anything that sets up a windows network interface. I'm an independent developer from Australia and have been working on Rouler for a bit over a year. It's been a challenging project to say the least, but I'm really happy with how it's turning out. I have spent a great deal of time building and throwing things away, starting over, belting the initial poc into something that I find intuitive... hopefully others do too! I've done all the testing, fixing and improving I can, so now it's open for public beta. I'd love to hear your feedback... and there are some specific points I'm interested in hearing about listed on the Rouler website. Please reply with any questions you might have. Thanks for reading! Brendan p.s. Rouler is "built in Rust" TM ;-) --- On AI (skip if you're sick of hearing about it): Since AI is the hot topic and people are naturally cautious about it, I'll add some quick notes about it, specifically about the driver development as that's the key thing to get right. The driver is hand written and every detail has been poured over many times over. I spent somewhere around 6-9 months manually building and testing just the driver, staring at Dbgview logs, wireshark logs, windows route tables, restarting VM's back to their snapshot and manually copying things across to start again. That's not always the most efficient way of doing things, but it's the way it had to be done. If I had tried to vibe code it Rouler simply wouldn't exist. I did try to lean on AI at times, but it constantly sent me in the wrong direction, told me things weren't possible, tried to take shortcuts and implement poor performing trade-offs. It also loved to hallucinate the windows api. Keep in mind this was around the Opus 4.1 - 4.6 days. Outside of the driver, in user mode land, AI has crept more and more into my workflow. I've had a lot of success utilising the latest models in the app in particular, and I purposefully separated the UI and core logic so I'm able to quickly iterate on the UI. I've also found AI very useful for scripting and refactoring. It has built some great scripts that would've taken me days or weeks to build and fine tune. https://rouler.io/ October 20, 2026 at 09:21AM

Show HN: we made every cloud work like one giant computer https://ift.tt/mr5D8FI

Show HN: we made every cloud work like one giant computer https://ift.tt/fiDPG3s October 20, 2026 at 10:16PM

Tuesday, October 20, 2026

Show HN: RawLink – Building a VPN protocol from scratch https://ift.tt/xEyikjb

Show HN: RawLink – Building a VPN protocol from scratch https://ift.tt/IV7cLex... https://ift.tt/SDJ9RQA October 20, 2026 at 12:29AM

Celebrating Our Safe Driver Award Winners

Celebrating Our Safe Driver Award Winners
By Andrea Buffa

Cassandra Griffin, also known as Cable Car Cassandra, is one of our Safe Driver Award winners this year. Being a Muni operator is an important and challenging job. It’s not easy to drive a cable car, streetcar or 40- or 60-foot bus through the streets of San Francisco. Yet, hundreds of operators have stepped up to the plate and get behind the wheel every day. They keep our city moving up and down San Francisco’s iconic hills. They help people get everywhere, including to work, school, the grocery store and the doctor. And of course, Muni is a great way to get to museums, concerts and sporting...



Published 2026-10-19T00:00:00Z
https://ift.tt/1gW6aPK

Show HN: ECG Signal Processing Starter Kit – Python, SciPy, and FastAPI https://ift.tt/GCHcnWq

Show HN: ECG Signal Processing Starter Kit – Python, SciPy, and FastAPI https://ift.tt/8VKL3jA October 19, 2026 at 08:00PM

Monday, October 19, 2026

Show HN: WhatsApp MCP running free on Cloudflare https://ift.tt/aBu3xNs

Show HN: WhatsApp MCP running free on Cloudflare I wanted my humble Claude on mobile to access my WhatsApp messages but the only options I could find either required WhatsApp Business or an actual server to run Baileys on. I wanted to run it for free on ClaudeFlare and with my personal WhatsApp account, so I built this. Important feature - it connects to your Google account as well as WhatsApp to grab the names of all your WhatsApp contacts, otherwise you get only phone numbers for many of them and search doesn't work properly. This is a single user install because it's both gray area and very private - so point your agent at the repo and let it set things up. https://ift.tt/yFNXpal October 19, 2026 at 03:06AM

Show HN: Ranet3 – High performance policy routed IPsec mesh SD-WAN https://ift.tt/vr3qtDs

Show HN: Ranet3 – High performance policy routed IPsec mesh SD-WAN btw this is already running on all my machines (including a macbook), and i've configured all of them to have routable public ip addresses ;) especially for the mac, my ISP is SFR (over coaxial connection) with only dynamic ipv4, i can use this to get stable v4/v6 addresses very easily for all my devices behind the router ios/android app soon^{TM} https://ranet3.com/ October 18, 2026 at 08:01PM

Sunday, October 18, 2026

Saturday, October 17, 2026

Show HN: 2026 Midterms Tracker blends polls and Kalshi/Poymarket odds https://ift.tt/REV7SAl

Show HN: 2026 Midterms Tracker blends polls and Kalshi/Poymarket odds https://ift.tt/caHCZkG October 16, 2026 at 11:49PM

Friday, October 16, 2026

Show HN: Endo – A Higher-Order Harness https://ift.tt/CxhvkKN

Show HN: Endo – A Higher-Order Harness Endo is a Higher-Order Harness (HOH). From the easiest concept to understand to the more complex ones, Endo gives you: * A single, simple UI to use any agent provider with your existing subscriptions, and hot-swap agents right in the middle of a session. * An orchestration layer, which I call HOH, allowing arbitrary composition of agents to achieve any workflow. A fun case I tried was asking Fable and Astra to mock a presidential debate. * An agent protocol that abstracts any agent. The key insight here is that every LLM is an agent—instead of treating the LLM as just one node inside an external ReAct loop. Endo was a concept formed while I was building OpenChart ( https://ift.tt/XdAKcVy ). To power trading workflows, I needed to support scenarios where strict determinism is required, while still keeping the flexibility of an agent's inference-time decision-making capability. A new form factor was needed between rigid n8n-style workflows and open-ended ReAct loop agents. Thus the creation of Endo. Endo is short for Endomorphism, a term rooted in category theory and functional programming. An endomorphism is a function that transforms an object into another object of the same type. Similarly, Endo itself is built purely on functional programming principles, relying heavily on Effect ( https://ift.tt/HMW8ByZ ). ..And if you have patience to speak technical jargons, Endo is: * An agent orchestration layer—Higher-Order Harness (HOH)—where an entire agent is treated the same as a single LLM call, enabling arbitrary composition of extremely complex workflows. * A way to abstract any harness into a standardized protocol, where raw models and agents behave the exact same way, in a KV-cache-friendly manner. * A workflow engine that enables arbitrary composition of agents with a single workflow language. It's completely open source, and if you think this idea is cool, let's build together. Just for the fun of it. https://ift.tt/BJT0MeX October 16, 2026 at 03:02AM

Show HN: Forwarder.cc – Static-site forms sent to your inbox, pay per message https://ift.tt/muKYgJC

Show HN: Forwarder.cc – Static-site forms sent to your inbox, pay per message TL;DR: 12 years ago I built a service that forwards simple HTML forms to an email address. I've been procrastinating on finishing it ever since, until today. You point your form at it and every submission lands in your inbox. It runs on credits, 1 credit = 1 message, no subscription. Perfect for static websites. — Hey folks, back around 2014, alongside my job as a software engineer, I was building a lot of static websites for my own clients, mostly small businesses that just wanted a simple site. To avoid headaches, I went fully static, often hosted on GitHub Pages and similar. But most clients also wanted a contact form, and a form needs a server running somewhere. I had my own weekend-hacked service for this, which literally just forwarded the form to the client's email. I didn't invent anything here: one service I particularly remember was FormKeep by thoughtbot, that I really liked. So I started building my own, mostly because I loved losing myself in side projects like this, and also because I was a cheap ass and thought I could do something similar for less, and without a subscription. By 2016 I had done about 90% of what I'm showing you today. I called it "The Great Forwarder". Everything was ready: backend, frontend, hosting, Stripe, landing page. I even had a designer friend help with the design (sorry, Valentin, if I've botched it since). Then I started another project, which took off right away and took all my attention for a while. Fun fact: that project has been using this service ever since, and almost every message ever sent through it came from there. So for years, I kept Forwarder.cc up to date, upgrading libraries and trying new ones: axios, got, Redux, Zustand, create-react-app, webpack, Vite… It became my laboratory for everything I wanted to explore, while always staying up and maintained (again, for my own use only). The only thing that ever held me back from launching it was a missing help center, and, more honestly, the fear of putting it in front of people. So today's the day: after 12 years of procrastination, I finally finished the help center. I know there are a ton of similar services nowadays, but anyway, what do you think of that help center? https://forwarder.cc October 16, 2026 at 12:17AM

Show HN: RDST – A local agent that watches Postgres/MySQL for query regressions https://ift.tt/ZFGqEYl

Show HN: RDST – A local agent that watches Postgres/MySQL for query regressions We noticed during the course of many many years of DBA related work that fixes to database issues and queries are always reactive. An entire database can fall over extremely quickly when an unbounded query grows without warning. Traditionally, DBAs hear complaints of slowness and follow a methodical process: - manually browse pg_stats or other database related performance internal tables - see which queries are slowest - figure out what indexes are missing - figure out which indexes are actually bad and slowing down writes - painstakingly implement a fix In the age of cheap intelligence, we decided that there is no reason we can’t have an always-on agent that is designed to do this job for you. Databases need something or someone that is always watching with a massive amount of contextual understanding to be able to take quick actions. We’ve watched the alternative play out repeatedly. One of our users’s checkout page went from loading instantly to taking 11 seconds in a single night with no code change. How? Well somehow their order table grew by 40M rows because BI team had injected historical data and suddenly postgres started doing full table scans. Sometimes routine operations have unintended results and can easily destroy your database. We wanted to catch these kinds of regressions instantly. So we built RDST. RDST is a desktop agent that runs on your PC and connects to PostgreSQL / MYSQL (read only) and compares every query against its own performance every minute. Every expensive query is automatically EXPLAIN ANALYZED, stripped of PII and sent to U.S. based frontier or open model providers to analyze which indexes are missing, how the query could be rewritten, and provides the fix. We then run a classifier model (JEV) to decide if you should be notified (is this standard behavior for this particular query?), and the full history of the query performance is kept for years. RDST also keeps track of your entire database health in general, and recommends more fixes than simply bad queries. Since it runs locally we can keep the database credentials stored in your OS Keychain (RDST never keeps them in its own storage layer), and the connection goes straight to your database (using a jump host or SSH tunnel for private connections). You can read more about how we handle data especially as it pertains to LLM use here. https://ift.tt/xsKNyLV We really want feedback from the community from people running Postgres and MySQL in production. We are giving inference away completely for free. Just as a reminder, RDST will NOT run any updates or indexes against your database at this time. We are considering a fully autonomous auto-pilot mode in the future, but for now we are leaving the actual fixes in your hands. Let us know what you think! https://ift.tt/ZjcKGNL October 15, 2026 at 11:39PM

Thursday, October 15, 2026

Show HN: Ask a technical question, get an animated explainer you can interrupt https://ift.tt/seRvwId

Show HN: Ask a technical question, get an animated explainer you can interrupt https://ift.tt/s2Bq67g October 15, 2026 at 04:10AM

Show HN: Dub Anything – Dub videos in each actor's own voice https://ift.tt/4mSyaov

Show HN: Dub Anything – Dub videos in each actor's own voice There are many movies and shows out there with neither subtitles or dubs in English (or any other language). Pretty much impossible to watch. With SOTA AI now directing the process, you can do it locally on your machine. You basically just clone the repo, open up Codex or Claude and tell it to dub the video you want in the language you want. The repo contains all the scripts and guidance I've developed over the past few weeks to create dubs that are watchable, as an added bonus the voices in the dub are the actors own voices which is really nice. Also it's self improving, each dub may modify the scripts for better fidelity. So feel free to push them back to the repo so everyone benefits. Thanks. https://ift.tt/64NGh5W October 15, 2026 at 01:19AM

Show HN: Sonia. Local AI Assistant Linux. 13Gb RAM, No GPU, Skills Supported https://ift.tt/MFvpJLn

Show HN: Sonia. Local AI Assistant Linux. 13Gb RAM, No GPU, Skills Supported https://ift.tt/Aq6BZtG October 14, 2026 at 09:38PM

Show HN: Petal, open-source CoScreen/ScreenHero finally free https://ift.tt/smSLdZC

Show HN: Petal, open-source CoScreen/ScreenHero finally free Hi HN! I’m Jason Thomas, one of the founders of CoScreen. As some of you may know, Datadog sunset the CoScreen service on July 31st. Four of us from the original CoScreen team have spent the last couple months building a free and open source pair programming tool inspired by those that came before us: It’s called Petal ( https://ift.tt/PqpM1mO ) Some history first, because when we started CoScreen we had hoped to break the sad and established pattern of this industry. Screenhero was an exceptional tool that a lot of us loved for pairing. Multiple cursors, low latency, you could click your partner’s editor, and just start typing. It felt like magic while we had it. Then Slack bought it in 2015, and shut down the standalone app in December 2017. When Till, Max, and I started CoScreen, we were aware of this history, and wanted to build an even more magical collaboration and screen sharing experience: the entire concept was “throw a window from your laptop up on someone else’s screen, and start collaborating with zero friction.” Datadog acquired us in 2022, and thus began the great adventure of adapting our real-time technology into Datadog products, while also continue developing CoScreen as a standalone tool from the Datadog ecosystem. Datadog invested in the product for years and we’re thankful for that. But CoScreen itself proved, like so many other screen sharing tool acquisitions, to be too tangential from the customer base and core mission. We instead built other communication features in Datadog, the integrations with other video platforms, and also its wildly successful MCP server. We weren't the only ones. Around was bought by Miro and shut down in March 2025. Multi (formerly Remotion) was acqui-hired by OpenAI in 2024 and shut down about a month later. It's nearly always the same story: a small team builds something hard that people love, a platform buys it for the team or the feature, and the standalone product doesn't survive the integration. So we decided firmly to do things differently this time. Petal is completely free and open source and we aren't monetizing it. If we lose interest or get hit by a bus, you can self-host it or fork it, and nobody can sunset it on you. Honestly it's a love letter to everyone in this community that supported us, believed in us, and to liberate collaborative screen sharing from this vicious cycle. We hope through this we can help foster a large and vibrant community around innovating in this product sector. What Petal does: shared windows show up as real windows on your desktop, movable and resizable, not tiles in a grid. Several people can share at once, everyone gets a labeled cursor, and you can click into any shared window to type and scroll. Rooms are persistent, so you click once to join "eng-sync" instead of passing links around. It runs on macOS and Windows (Linux is next, this time for real and you can help us!), plus a web app. Media goes over LiveKit. You can use our hosted instance with zero config, or point the app at your own LiveKit server with one docker-compose if you want the traffic to stay on your network or even use an entirely different video backend if you want to. The part that still feels strange to us: CoScreen took almost six years to build. The first version of Petal took under eight weeks, from scratch, with frontier models like Fable and Astra doing a lot of the work. Real-time video and window capture is some of the most unforgiving code we have ever written, so we didn't expect that. We will do a proper writeup on what worked and what didn't, and are happy to answer questions about it here. Till, Darren, Max and I will be in the thread. https://petal.live/ October 14, 2026 at 11:53PM

Wednesday, October 14, 2026

Show HN: Treesum – Replace MS Excel/Project with a Code Editor https://ift.tt/dRyh3ZG

Show HN: Treesum – Replace MS Excel/Project with a Code Editor # Intro The goal of this software is to make it easy to get the plan that's in your head onto the page. Start with the outline then add details. Then more details. Then numbers: costs, time, quantities. Then organize and categorize with #tags. All the sums, graphs and pivot table functionality happens automatically in the Calcs, Timeline, Stats views. And everything looks nice without you having to format it. Currently, it's all local, saved in your browser. Save your plan permanently by downloading the '.tsum' file. Open (upload) the '.tsum' to start working again. Everything happens in the browser. The files are stored where ever you like. The '.tsum' file is just text - human and AI readable. Use it to plan anything. We hope it works like your brain does - by organizing things in trees. # Story This software is entirely vibe-coded. It had to be - none of my developer friends would help me out. The front end JS on this app is too complex for a part time developer like myself. I've had this idea for a while and was only able to bring it to life because of AI. It may not gain traction, but at least I can put it out there, use it myself, or stop thinking about it altogether. It's amazing to see it and actually use it - to know if my idea was good or not, at least for me. And I'm actually happy with it and have been using it. If you have thoughts about the idea, feel free to let me know. I'm open to suggestions for improvement. # Disclaimer This tool is mainly intended to help with project planning. But it can be used for any data that looks more like a tree than a table. Creating a quote or estimate for one-off projects is my favorite use case. The varying structure of costs across lumber, electrical, concrete and labor fits well. Obviously, it doesn't replace all the many things Excel can do. It tries to improve on MS Project by making it easier to get your schedule on the page by coding into an editor instead of poking at menus in a GUI. It is still a proof of concept at this point, not a bullet-proof software package. If there's interest, it will be developed further. For now, it's good enough for me. # Roadmap I want this software to be the Excalidraw of Excel: free, simple, browser-based and fun to use. There are great things that Excalidraw does that would require servers and more costs. These features could be turned into a paid product if there is interest. So, if you're interested, please let me know: treesum.app (at) gmail.com. # Thanks HN This project would not have been possible with out AI. But also not without HN. Reading HN nearly every work day really shapes how to think about software and presenting it to people - especially for someone who is not a full-time developer. It's a great community and I've happily been a member since (at least) 2013. https://ift.tt/tOe0Buw October 13, 2026 at 10:25PM

Tuesday, October 13, 2026

Show HN: Brickbrag – A multiplayer brick-building world in the browser https://ift.tt/P2sVkKM

Show HN: Brickbrag – A multiplayer brick-building world in the browser https://brickbrag.com/ October 13, 2026 at 02:33AM

Show HN: Yagi, Rust DSP Library https://ift.tt/FmX0bEV

Show HN: Yagi, Rust DSP Library Hi HN, I'm a big fan of the liquid-dsp C library and thought it'd be fun to bring it over to Rust. I'm calling this library Yagi DSP. liquid-dsp has more than 1300 tests and yagi now has ported and passes more than 95% of them. I've just finished a major refactoring of the library with lots of API churn now behind me and I think it's now ready for external users. I've still got a lot more I'm hoping to do with it including a streaming graph/dataflow library that I'm building on top of yagi. My goal with that is to create something that's easily embeddable in applications. The browser demo linked in the README is just a very basic example to show how different modems work in the presence of noise, but it really does use yagi via wasm-bindgen. I think it's a fun 5 minute diversion if you've heard terms like QPSK or QAM but aren't sure what they mean. You can try out the demo here https://ift.tt/KeHPw17 https://ift.tt/lfdJpju October 13, 2026 at 01:52AM

Show HN: I bought a bunch of 'smart' devices. AI was able to hack most of them https://ift.tt/SxoWKqI

Show HN: I bought a bunch of 'smart' devices. AI was able to hack most of them https://hwrebench.com/ October 12, 2026 at 11:29PM

Show HN: Two browser games set inside one real Gaussian-splat scan https://ift.tt/FdqBb2j

Show HN: Two browser games set inside one real Gaussian-splat scan https://ift.tt/DEvR63L October 12, 2026 at 11:12PM

Monday, October 12, 2026

Show HN: THX-01 – Open-source decision model, free API, 60M+ tokens processed https://ift.tt/lTzHswc

Show HN: THX-01 – Open-source decision model, free API, 60M+ tokens processed https://twitter.com/reversedoofz/status/2109228322752471304 October 12, 2026 at 03:01AM

Show HN: LLMxRay an open-source observability tool for LLMs https://ift.tt/fM5JAbV

Show HN: LLMxRay an open-source observability tool for LLMs https://ift.tt/gTfcnJy October 12, 2026 at 02:47AM

Show HN: Kindlefall a 3D ARPG in the browser, built with Three.js https://ift.tt/n9BSsmw

Show HN: Kindlefall a 3D ARPG in the browser, built with Three.js https://ift.tt/pNJ82QB October 12, 2026 at 12:08AM

Show HN: HarmoNova: A modern, customizable Hacker News reader for Chrome https://ift.tt/0du5Mvh

Show HN: HarmoNova: A modern, customizable Hacker News reader for Chrome https://ift.tt/yNQUH0L October 12, 2026 at 12:12AM

Sunday, October 11, 2026

Show HN: ManimGX – Manim's API on a Rust/wgpu engine, for 3D videos in Python https://ift.tt/mEr6nT8

Show HN: ManimGX – Manim's API on a Rust/wgpu engine, for 3D videos in Python Video as code took off with the Opus 5.5 release. People now make videos by writing code, with Remotion, HyperFrames and others. We wanted the same for 3D videos. You can use something like Blender, but it's heavy to install and slow to render. So we made ManimGX: - Lightweight: a 65–110 MB download, depending on the OS - Easy to install: pip install manimgx (Python 3.13+), with no system dependencies - Cross-platform: macOS, Windows and Linux, and even the browser via Pyodide and WebGPU - Blazingly fast: a Rust + wgpu engine, 90.6× faster than Manim CE and 18.7× faster than Blender Workbench, from launch to finished MP4 - Compatible with Manim Community Edition's API, with LaTeX and Typst math built in Now it's much easier for anyone with a coding agent to make 3D computer graphics videos. Repo: https://ift.tt/0zkOlqA Docs: https://ift.tt/UYa6gNn X post: https://ift.tt/y4zTqH0 Happy to answer any questions! https://ift.tt/0zkOlqA October 11, 2026 at 04:03AM

Show HN: Try Free Long-Term Memory for AI 50M-Token Window https://ift.tt/jwVoLsD

Show HN: Try Free Long-Term Memory for AI 50M-Token Window https://ift.tt/uPA4HdT October 11, 2026 at 03:06AM

Show HN: Throw Alice and Bob into Sagittarius A* https://ift.tt/e8OGIzu

Show HN: Throw Alice and Bob into Sagittarius A* Black Hole Lab is an open source physics simulation of a rotating black hole and two observers, Alice and Bob. You can launch Alice and Bob on paths around or into the black hole and watch events play out. The simulation lets you see a slice of the physics with one or two dimensions of space plus one of time. As a fun extra, Alice and Bob each have a beacon that can transmit a radio wave in all directions. The simulation calculates and shows the wavefront of these signals, accounting for the warping of space and time by the black hole. The simulation also records whenever Alice and Bob receive each other's transmission. The simulation takes pains to respect Einstein's equations of general relativity. To the precision of the numerical integration, the effects shown in Black Hole Lab are really what the math of general relativity says will happen. Black Hole Lab specifically uses the Kerr metric, which is an exact solution to Einstein's equations of general relativity for a rotating mass. That said, physicists agree that general relativity cannot be the final word on black hole physics. Nobody can say what would really happen to Alice and Bob. My original goal for black hole lab was to try to understand the strange time compression effects at the inner horizon, which physicists call infinite blueshift. IMHO, Black Hole Lab succeeds in showing this effect in an understandable way. I added a specific discussion of infinite blueshift in the readme. https://ift.tt/9VyfaBO October 11, 2026 at 02:58AM

Show HN: A functioning Celery Man computer https://ift.tt/prGPbqV

Show HN: A functioning Celery Man computer Hi HN! It dawned on me that the latest AI models (Minimax H3 Max / Audio, GPT-6 Luna) can finally recreate the computer from the classic Tim & Eric Celery Man sketch. I spent a few days creating it: it has 100% parity with the original script, plus anything you ask for (doggy woof woof man or potato boy). Happy to answer any questions about the pipeline! https://celeryman.fun/ October 10, 2026 at 11:38PM

Saturday, October 10, 2026

Latine Heritage Month Spotlight: Supporting Spanish-Speaking Communities

Latine Heritage Month Spotlight: Supporting Spanish-Speaking Communities
By Glennis Markison-Busi

Beatriz Flórez Huertas shares information about SFMTA programs. This Latine Heritage Month, we are celebrating the work of SFMTA Community Liaison Beatriz Flórez Huertas. At the heart of her job: helping Spanish-speaking communities get around San Francisco. And Flórez Huertas is especially sensitive to what newcomers might be facing. Starting with empathy When Flórez Huertas came to the U.S., she had no connections. She had to learn how to navigate transit, find housing and build a career all on her own. “When you don’t have family here, who do you rely on?” Flórez Huertas had to ask. “Who...



Published 2026-10-09T00:00:00Z
https://ift.tt/dbaPCAS

Show HN: The rarest tech books and docs you've probably never read https://ift.tt/vauoNCh

Show HN: The rarest tech books and docs you've probably never read https://readrare.com/ October 9, 2026 at 11:09PM

Friday, October 9, 2026

Thursday, October 8, 2026

Show HN: Pointless but mostly-exact clone of Hacker News https://ift.tt/3gokGAr

Show HN: Pointless but mostly-exact clone of Hacker News Source code: https://ift.tt/xFpRTs6 I had more things I wanted to do with this, but I should probably admit to myself I probably won't be. The original idea was for https://ift.tt/lUIizhx to be "Hacker News, but all the comments are AI." Right now it's "Hacker News, but all the comments are the same as the real HN." Hence, it's completely pointless. Special thanks to dang for collaborating -- he even suggested the name for the codebase, "sharc". Development time was about four months of near daily work: https://ift.tt/ia5qtwb... Some days I'd spend a solid 16 hours on this. What's the point? None, really. Just to test the limits of my abilities and prove to myself that I could do what pg did. It's an extremely efficient port of HN to Common Lisp. One of the project's goals was to be high performance. According to benchmarks, it can generate pages very slightly slower than real HN. (dang shared some timings on a particularly busy page, along with how many views it got over a certain time period, for benchmarking throughput. I never got around to verifying whether I can handle 24 million views a day, though, so I'd imagine something might break if you scale this up. On the other hand, I think it'll hold up.) If you're particularly offended that this is copying your comments, claim your account by going to your profile (for example, I would go to https://ift.tt/la4fgmh ) and then click "claim" at the bottom. It'll ask you to put a 6 digit code into your real HN profile, at which point you'll be able to reset your cloned profile's password. Log in, go to your profile page, and set "redact" to "yes", the same way you'd set "showdead" to "yes" on HN. So, why make this? Eh, call it an art project. That's code for "It would've been a lot funnier with AI generated comments, but I seem to have stopped working on this for now." I'll post an update someday, if I can figure out how to do it without paying hundreds of dollars of API token prices. /ask and /show are missing. Those were the only two features left to clone. But pretty much everything else is there. It's been running for a couple months now, so I suppose it's stable enough for a public showing. Not that there's any reason to look. Shoo! Go find a more worthy project to devote your attention to. :) Kind of melancholy admitting that I spent four months with only something pointless to show for it. But then again, here's the punchline: go to any random comment on HN, then in the url change .com to .lol and you'll see an almost pixel perfect recreation. For example, https://ift.tt/5mI1rBq Sadly you can't form a loop, because if you edit your original comment with a link to itself, you'd only be able to go from HN to .lol to HN. But you could list both and switch between them as much as you want. For example: https://ift.tt/szmYMt5 https://ift.tt/3gokGAr This project was one of the most technically demanding things I've ever done. People look at HN and go oh, that? That looks easy. If you think so, I invite you to write it yourself -- it's an exercise that'll certainly make you a better programmer, and gain appreciation for how many subtle features we enjoy here on HN. Ha, and I just discovered a new one. I mixed up the "title" and "url" boxes just now. HN popped up a nice looking overlay that said "please enter a URL", pointing to the actual url box. https://ift.tt/l86q2Vr The HN team is always adding something or another, even if it's not always visible. Normally I'd dive into this and find out how it works and clone it, but ... eh, I'll settle for a 95% exact clone. https://ift.tt/lUIizhx October 7, 2026 at 11:35PM

Show HN: getrequest – Never lose an API request https://ift.tt/ObChzTH

Show HN: getrequest – Never lose an API request https://ift.tt/eD1gCqU October 7, 2026 at 11:31PM

Wednesday, October 7, 2026

Show HN: Browser-Based F1 Game https://ift.tt/t2Dykz7

Show HN: Browser-Based F1 Game Hello HN, I vibecoded a F1-styled game and it works in the browser. Check it out! https://ift.tt/yfC6PDG October 6, 2026 at 11:37PM

Show HN: Session-continuity, cryptographic proof of session chains https://ift.tt/lw8N1fY

Show HN: Session-continuity, cryptographic proof of session chains https://ift.tt/wQlIUhP October 6, 2026 at 08:22PM

Tuesday, October 6, 2026

Show HN: Live carbon intensity and power prices for 15 European grids https://ift.tt/v8FKnk7

Show HN: Live carbon intensity and power prices for 15 European grids https://ift.tt/7VCx0oc October 6, 2026 at 01:03AM

Show HN: Flash-Agents – DSH as MCP for Claude https://ift.tt/4kmDSq9

Show HN: Flash-Agents – DSH as MCP for Claude I do a lot of work using claude and codex. I use plenty of sub-agents. But nothing balances bang for the buck as good as deepseek v4.1 flash for me. So I thought, why not use the deepseek harness as MCP and drive it from claude as an orchestrator. I am probably not alone with this idea, but I haven't found something comparable. I wanted to fan out sub-agents and get back meaningful results. Well, say hello to flash-agents. With ollama as a backend driver no more training on my data (I think), and its pretty fast. I was driving a few billion tokens through that now without any issues. So I thought I'd open source it. What works for me, might work for others. Let me know what you think. If you know anything better, always welcome. Not claiming my solution is yay, but it works for me so far, and I get real productivity gain out of it. https://ift.tt/x1Wr5DL October 6, 2026 at 12:32AM

Show HN: Nightwatch – a Mac menu-bar app that tells you when tonight is clear https://ift.tt/2CQ1WAj

Show HN: Nightwatch – a Mac menu-bar app that tells you when tonight is clear Here in the north of England clear nights are at a premium, and it's never guaranteed that you'll be able to see anything but cloud. That's why I developed Nightwatch, so that I could be notified when one of those precious few nights where I could see into the heavens was available. Finding out whether tonight was worth setting up meant reading forecast charts every evening, usually to learn that it was not. Nightwatch does that reading for me. It sits in the Mac's menu bar and refreshes the forecast every 30 minutes. An hour before sunset it sends one notification, and only if there is an unbroken run of clear sky in astronomical darkness long enough to image in. Otherwise it says nothing: no news means "clouds". I hope this is useful for other hobbyist stargazers too! When I was a child I wanted desperately to be an astronaut or a dinosaur. I'm now old enough to be the latter and was born in a country where the former was never an option. I've had a fascination with the stars since a a friend of my father gifted me a telescope, and have faded memories of sharing time with my father staring at the stars. My father passed away a few years back and the memory of those nights came back, along with the want to share the same experience with my kids and grandchild. The app uses two forecasts: Apple's WeatherKit is the main source and Open-Meteo is a second opinion. When they disagree, the alert says so instead of averaging them. Thin high cloud counts for half. Stacking many short frames works through a veil of cirrus, so treating it as full cloud threw away usable nights. It works on your own horizon: hills come from terrain data, and you set the houses and trees in each direction, so they are accounted for when it says what is up. It works out, a year ahead, when the Moon will pass in front of a planet, a bright star or the Pleiades as seen from your site. You don't need an account. What leaves the Mac is the coordinates of the place being forecast, sent to the forecast and sky-survey services listed in PRIVACY.md. Limits: Mac only, and the aurora alerts are UK only. The worldwide light-pollution data is new this week. I have checked it against Britain's finer grid and a handful of cities, so I would especially like to hear from people elsewhere whether the darkness it suggests for your site looks right. https://ift.tt/TQ37CaN October 4, 2026 at 03:01PM

Monday, October 5, 2026

Show HN: Glashütte Trash Clock – A 30-minute pendulum clock made from trash https://ift.tt/DAR961K

Show HN: Glashütte Trash Clock – A 30-minute pendulum clock made from trash This is a functional 30-minute pendulum clock entirely from discarded materials—cardboard, zip ties, tape, a yardstick, and a paperclip escapement, built in the German Eldorado of precision watchmaking: Glashütte. It also acts as a reference clock for GTC, a new satirical universal time standard. https://ift.tt/gGvbcOW October 2, 2026 at 12:03PM

Show HN: Jev-pages – Building landing pages real time with Jev https://ift.tt/lBcbFL2

Show HN: Jev-pages – Building landing pages real time with Jev An experiment using Jev to generate landing pages in real time. Jev is great at picking between different options so I attempted to break down the langing page UI into a set of choices for the model to choose from. How this works: 1. Users type what kind of page they want and Jev decides what each line is (headline, fact, assertion etc.) 2. Jev makes choices for each layer of the page (opening, stage, light, depth etc.). Parameterizing design is hard (impossible?) but this took some tuning with Claude 3. A full page is constructed with a single call of about 90 questions. Of course using an LLM would be more prudent for step 1, but I wanted to check the limits of Jev's understanding (it works pretty well in my opinion!). https://ift.tt/t0Gqp8T October 4, 2026 at 11:00PM

Sunday, October 4, 2026

Show HN: Revline – an AI web app that researches TikTok and Instagram for you https://ift.tt/QDUeTug

Show HN: Revline – an AI web app that researches TikTok and Instagram for you I build revline because i was trying to figure out how viral content works across tiktok and instagram, since i am mainly developer, i was confused about how to create content that gets me users. Actually going viral requires single founder ( me ) to upload 3-4 videos a day, brainstorming all the formats was not effective to do alone, so i build the agent that does all the scrolling for me. would appreciate feedback https://tryrevline.com/ October 3, 2026 at 11:50PM

Show HN: Automating my 35mm film scanning pipeline https://ift.tt/7nPRMvb

Show HN: Automating my 35mm film scanning pipeline https://ift.tt/BPq618D October 3, 2026 at 11:05PM

Saturday, October 3, 2026

Show HN: Our space game has a built-in RISC-V emulator that runs Linux https://ift.tt/RTAM1fw

Show HN: Our space game has a built-in RISC-V emulator that runs Linux We're a tiny indie studio, all with a background in the demoscene and for about 3 years now we're developing a space planet terraforming game called SEEDS - Echoes Beneath the Sands. Our protagonist Naxiah is stranded on a small, desolated planet. You're working for an intergalactic distributor of seeds and terraforming equipment, to kickstart new planets in far away galaxies. You must deliver seeds and utilities to an unchartered region, but on your way, you crash on a small planet. Luckily, you have some equipment with you in the ship, so you're able to spawn a base and survive. But for how long? And is the planet really deserted..? :) Well, of course not, there are aliens and other space creatures. And of course, there's ROBO RB-23, which accompanies your adventure. The game is written in Object Pascal and uses our own game engine PasVulkan, our own physics engine, as well as our own RISC-V 64-bit emulator PasRISCV. We love to build stuff, a lot of these things are FOSS. The emulator is quite complete (even with RVV, but that's way too slow emulated to be useful) and runs a stock kernel (6.18.3 as of today). We're using Alpine Linux for our base distribution. All our in-game programs to interact with the planet are native RISC-V Linux programs. We also have our own (free and open source) scripting language POCA (class and prototyped based, JS/Lua inspired, which makes it quite easy for us to script things like HUD, animal behaviour, our story flow graph, etc. We have most of the wiring ready for players to be able to program and reshape and populate the whole planet in automation, although it's not our primary concept for the game (building stuff by hand, making the planet beautiful is also fun). As it's a normal Linux system, you'll be able to use Ruby, Python, or even Rust, C, C++, and Go to change and automate your world. We're also thinking of making a bunch of small games which you can play inside the game, in the base on a computer, on an arcade machine, or in the spaceship. And of course, it also runs DOOM. We already prototyped a small 2D space shooter and a small arcade game, both playable within the game. We also feature a table with hologram games to be played, e.g. chess and a certain block game. We also plan to make this hologram game engine available from the computer, which means, you'll even be able to program own hologram style games. We generally want to make the in-game computer more hackable in future, so that people can create and share their own little games. Currently, it's only a sandbox game (with beginnings of automation), to build stuff with our pre-made items. You can also assemble these to other, ready-made and shareable bigger items. This is the foundation for us to further develop survival and complete our story mode. Our game is still under active development, and we finally got our Steam page ready. We have tons of other things planned, but right now, it's more about polishing and quality for the Early Access. You can watch some videos and screenshots on our website. And we'd love to read your thoughts about his. It has been quite a ride, so far.. https://againstallodds.games/ October 2, 2026 at 04:10PM

Show HN: We built a real-time desktop companion for patient's telehealth visits https://ift.tt/ohHfXZe

Show HN: We built a real-time desktop companion for patient's telehealth visits Hey HN, Some friends and I built an app called Sidekick that joins your telehealth visits in real-time. It explains medical terms and suggests useful questions, including ones you may not have thought to ask. After the visit, it provides a summary including next steps, so you can focus on the conversation instead of taking notes. The idea of Sidekick came from our team's experiences with healthcare. Our founder, Rahul, had stage three cancer at 17. His mom had to manage everything around his care: taking notes through treatment, figuring out what questions to ask, etc. A decade later and he’s now in remission, but still sees a lot of specialists and deals with the same challenges. Another teammate became a caregiver after his dad had a severe stroke. He found himself taking notes, looking up medical terms, and trying to keep track of what was said during every doctor visit. Others have dealt with situations like this when navigating pancreatitis and other serious health issues. These experiences got us interested in how we might be able to reduce the burden on the patient or caregiver. A lot of products focus on simply recording or summarizing the visit. That's useful and a step in the right direction, but we kept coming back to the fact that a lot of the challenge originates while the conversation is still happening. If you can catch something in the moment, you can address it with your clinician immediately and potentially lead to better outcomes. If you realize you missed something after the visit, then you have to try to get another appointment (and in SF I often can't get another doctor visit till 2 months later). So we built Sidekick, to help patients and caregivers during a visit in real-time to translate medical jargon and suggest useful questions, ideally without becoming a distraction. If you want to try it, you can download it on our website. Sidekick is desktop-only for now, but we’re working on a mobile app for in-person visits. We would be especially interested to hear feedback on the live part of the experience. What are your thoughts on the balance between live help vs after-visit? Would something pre-visit be more helpful? https://openhand.health October 1, 2026 at 07:57PM

Friday, October 2, 2026

Show HN: Open-source model routing for coding agents at Astra-level performance https://ift.tt/1B89J7V

Show HN: Open-source model routing for coding agents at Astra-level performance A few months ago we started building a model router for coding agents because we thought we could outperform any single model with an ensemble approach. Recently we’ve achieved that milestone and I want to talk about how we did it. First of all, a quick explanation: the Weave Router ( https://ift.tt/X4a1wsA ) plugs into any coding agent (e.g. Claude Code or Codex) and intelligently switches between LLMs. So, for example, Astra handles tricky debugging or complex system design tasks, and Deepseek v4 Flash handles simple frontend updates. What we’re announcing today is our new routing model, which we’re calling Weave Router 2.0. We benchmarked 2.0 against GPT-6 Astra on Terminal Bench 4.0 and SWE Atlas. On both benchmarks, the router had equivalent pass rates. On Terminal Bench, the router hit 52% of Astra’s cost, and completed tasks 2.2x faster. On SWE Atlas, the router cost 54% as much as Astra and ran 2.5x faster. (Full results on our website at https://ift.tt/wRaZhjQ !) It turns out training a model to route effectively - taking into consideration model capabilities, costs, cache awareness, and more - is a really hard problem! I want to talk about three ways we were able to improve so much over the last few months: 1) a new architecture, 2) larger training data set size, and 3) smarter cache-eviction impact calculation. 1) a new architecture. Our initial approach used an RL model without many priors. While RL is still an important part of the story, the cost of fully exploring the space of routing decisions is very high, so we’ve taken some shortcuts that have significantly improved performance. Consider how large the search space for the routing problem is. Take a typical coding agent session, with ~100 agent turns (i.e. 100 LLM API calls). Technically there are 100 chances to select a model. If we assume a roster of ~10 models (of course there are lots more but we can remove any that are Pareto dominated), then there are 10^100 possible paths through that session. We simply cannot explore all of them! So that's why clever tricks to shrink this space are so important. In particular: we trained a hidden Markov model to trace the session state, then a classifier maps the session to one of a few buckets of similar models. Using the HMM allows us to evaluate not just where a session is currently, but how it got there . We've gotten significantly better performance on bucket selection by incorporating that information - we believe this is because two sessions that might look quite similar to a naive classifier are much better distinguished by this HMM approach. Using this HMM + classifier to select a bucket first significantly shrinks the space to explore, by throwing out most models that could not reasonably serve the given session. This rearchitecture was the single biggest performance unlock! 2) larger training data set size (much less technically interesting but still an important part of the story). By using frontier LLMs to help us label a larger and more diverse set of coding agent sessions, we were able to bootstrap the two models discussed in 1) to a better state, while also providing even richer reward signals for RL. 3) smarter cache-eviction impact calculation. One of the hardest parts of routing well (if you care about saving money) is using the model caches intelligently. We built a subsystem that can calculate the expected value of switching models (and thus paying a high one-time cost to fill up a different cache) much more accurately, helping us avoid costly and unnecessary switches in more cases, while still switching when the benefit outweighs the cost. This is where most of our improvement on cost has come from. We still have a lot of room to continue to improve (we won’t rest until we’re consistently beating Astra/Fable, not just tying!) but matching frontier model performance was a huge milestone for our routing model, and in my opinion validates our initial hypothesis that an ensemble of models can do better than any single model ever could. Our router is open source ( https://ift.tt/X4a1wsA ) so anyone can try it out. Or if you prefer you can use our hosted version ( https://ift.tt/wRaZhjQ ). September 30, 2026 at 10:28PM

Thursday, October 1, 2026

Show HN: Domainpuff.com – Find memorable domain names within your budget https://ift.tt/Kuv4xCr

Show HN: Domainpuff.com – Find memorable domain names within your budget Hi, Bruno here, creator of DomainPuff. Just launched this and would be awesome to have your feedback on it. Just put your business idea on the search box and your budget. It will find memorable domain names that are currently available and within your budget, with the link to acquire the domain if desired. So now you don't have to go back and forth from ChatGPT to NameCheap to find a domain for your next venture. Cheers! https://domainpuff.com/ October 1, 2026 at 01:25AM

Show HN: Strata – an expressive semantic layer that can say no to your LLM https://ift.tt/3IGrdJb

Show HN: Strata – an expressive semantic layer that can say no to your LLM Hello HN, I'm Ajo and I built Strata. I spent 4 years at Netflix solving self service for non-technical business users. I think I cracked it with my unique approach to semantic layer design. The key challenge is balancing expressiveness with ease of use for our non technical colleagues. It just so happens that focus made it work pretty well with LLMs too. Strata is a full stack solution. It includes a semantic layer, dashboards, subscriptions, and google sheets exports. All of it can be done view agent conversation or via MCP. Some key concepts and features: - Names are strict. Only one thing called Revenue can exist in a project. If revenue is mapped to multiple tables, the query grain plus speed will decide table. - Strict naming conventions lends itself to enabling Automatic data blending acrros fact domains. - Partition and Aggregate aware semantic routing. This allows you to load a portion of your data into a faster compute engine like Druid or ClickHose, while keeping full history in trino or something cheaper. The query engine will choose the faster tier if the query can be resolved there. - Complex measures: out of the box support for snapshot, LOD (include/exclude), Compound, and Auto leveling compound measures. - On top of the semantic layer users can create custom calculations that span fact domains. - Another interesting feature is the ability to create cohorts and apply as filter to an entire query or single measure within a query. We are deliberately not building a semantic layer that your BI tools connect to. I think that is a dead end. We have apis, and mcp for anything custom you want to build on top. Try it free on docker: https://strata.do/try/ Docs here to get you going: https://strata.do/docs/ This is an early beta version. It is NOT open source. However, the free tier includes up to 25 users. You should be able to run it entirely on your machine with docker. I would love to hear your feedback. Especially, those working with Looker and Cube. Thanks for reading! https://strata.do/try/ September 30, 2026 at 08:29PM

Show HN: Thesis, checks every SEC filing against why you own a stock https://ift.tt/yRa2SXv

Show HN: Thesis, checks every SEC filing against why you own a stock https://www.mythesis.ai November 6, 2026 at 10:57PM