Show HN: Inertia – Not your Grandfathers animation editor https://ift.tt/0PbBOYa

Show HN: Inertia – Not your Grandfathers animation editor https://ift.tt/K37HyMS August 9, 2026 at 03:57AM

Show HN: A Discord bot running in a 4MiB microVM https://ift.tt/rx8diA3

Show HN: A Discord bot running in a 4MiB microVM https://ift.tt/GquysbB August 8, 2026 at 11:04PM

Show HN: Algebruh - Cross-check arithmetic claims with Z3, cvc5, and Lean https://ift.tt/ytLl4vO

Show HN: Algebruh - Cross-check arithmetic claims with Z3, cvc5, and Lean https://ift.tt/fcNwrIH August 8, 2026 at 11:34PM

Show HN: Check if any of the $656M in unclaimed royalties at The MLC is yours https://ift.tt/qYFMHKa

Show HN: Check if any of the $656M in unclaimed royalties at The MLC is yours https://pub.doub.ly/ August 7, 2026 at 11:05PM

Show HN: Zaivern Code – a Rust cockpit for parallel AI coding agents https://ift.tt/gC24wh3

Show HN: Zaivern Code – a Rust cockpit for parallel AI coding agents https://ift.tt/JdxwrWs August 8, 2026 at 12:53AM

Show HN: Mousecrack – Teaching an LSTM to move a mouse like a human https://ift.tt/t1VPjba

Show HN: Mousecrack – Teaching an LSTM to move a mouse like a human https://ift.tt/0Tfzg8v August 7, 2026 at 10:23PM

Show HN: ARF – a record format for AI evaluation runs, with reproducible digests https://ift.tt/eCOY5Hy

Show HN: ARF – a record format for AI evaluation runs, with reproducible digests https://www.korvo.xyz/arf August 7, 2026 at 04:55AM

Show HN: AI Tutoring with Visual Grounding https://ift.tt/pXdYANx

Show HN: AI Tutoring with Visual Grounding I've always felt that AI tutoring as we see it now is going in the wrong direction. I made Knowable as a way to see if it's possible to have a real AI tutor. Because of hardware limitations it can only be used on Macbooks 2023+. Let me know your thoughts! https://useknowable.ai/ August 7, 2026 at 05:34AM

Show HN: Learn System Design, one campaign at a time https://ift.tt/ScTMFku

Show HN: Learn System Design, one campaign at a time https://scalequest.io/ August 7, 2026 at 03:25AM

Show HN: Pokémon Emerald Ported to Raspberry Pi Pico 2 https://ift.tt/LxUSFWg

Show HN: Pokémon Emerald Ported to Raspberry Pi Pico 2 Pokémon Emerald ported to the RP2350 microcontroller. No emulator, 60 fps HDMI output. Recompiled from ARMv4T to Cortex-M33 and the Game Boy Advance's video hardware is reimplemented in software on the second core. https://ift.tt/4Xkgre5 August 7, 2026 at 03:19AM

Show HN: LiminalML – Study ML or SWE at interview depth, grounded in your resume https://ift.tt/TPu2D7a

Show HN: LiminalML – Study ML or SWE at interview depth, grounded in your resume https://liminalml.com August 5, 2026 at 11:09PM

Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone https://ift.tt/jUEVPz5

Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone https://ift.tt/QJCH81n August 5, 2026 at 01:14AM

Show HN: My tool scanned 256 AI-built apps and most had exposed credentials https://ift.tt/Y3xCTOG

Show HN: My tool scanned 256 AI-built apps and most had exposed credentials All of a sudden everybody wants to build with AI. People in hell want ice water. Built something with AI and don't know if it's secure? Try necktochoke. https://ift.tt/45A2bvw August 5, 2026 at 01:42AM

Show HN: TormentNexus – Local-first Go control plane with persistent memory https://ift.tt/ctsfHVN

Show HN: TormentNexus – Local-first Go control plane with persistent memory https://tormentnexus.site August 5, 2026 at 12:47AM

Show HN: Spellfolio – my stock market game with news events and inside info https://ift.tt/gzYGOsU

Show HN: Spellfolio – my stock market game with news events and inside info https://ift.tt/4aZRHLn August 4, 2026 at 04:08AM

Show HN: Freqcast, an Android radio player that finds streams from a website URL https://ift.tt/pUQ0gZB

Show HN: Freqcast, an Android radio player that finds streams from a website URL Hi HN! Not every internet radio station is listed in a directory like Radio Browser. For a lot of them, the only way to actually listen is to dig the stream URL (.mp3/.aac/.m3u8) out of the station's website by hand — and that's before you even find a player that isn't full of ads or locked to its own catalog. Freqcast lets you paste the station's website instead of the stream URL directly. It first checks the Radio Browser catalog, then scans the website itself, discovers a playable stream, verifies that it works, and adds it to your library. In many cases, you never have to hunt for the URL yourself. No ads, no tracking, no account — everything lives locally in the app. Your station list can be exported as JSON, and imported from JSON, OPML, M3U, or PLS. No Play Store listing — grab the APK from Releases. F-Droid submission is in progress. Would genuinely love feedback! https://ift.tt/JlFgTdY August 4, 2026 at 03:05AM

Show HN: Golars (Go Equivalent of Polars) https://ift.tt/JACc1dh

Show HN: Golars (Go Equivalent of Polars) https://ift.tt/tXwhgnA August 4, 2026 at 01:30AM

Show HN: Framer Theme Toggle Component for Light and Dark Mode https://ift.tt/vjWraQ5

Show HN: Framer Theme Toggle Component for Light and Dark Mode A free light and dark theme toggle for Framer that remembers what visitors pick, plus a code override for the components that colour styles cannot reach. https://ift.tt/syzJwV5 August 3, 2026 at 12:49AM

Show HN: My public second brain – 660 notes, 15 years, open source https://ift.tt/D1rIPeH

Show HN: My public second brain – 660 notes, 15 years, open source Author here. ~660 notes published from a private Obsidian vault of 8,360 (3M words). Started in OneNote around 2011, moved to Obsidian in 2021 [1], imported everything with a Python script [2]. Notes are compounding over time, and that is where my writing comes from. The Semantic Layer note started in 2022, became a four-part blog series, then a chapter of my book. Materialized Views, One Big Table, dbt and OLAP were separate notes written years apart. I only later noticed they were the same pattern, and that became another chapter. Publishing: add #publish to a note, run `make deploy`. Quartz + Hugo, rsync to my own server [3]. Code [4]. Semantic search over the graph [5]. [1] https://ift.tt/b6vjiRQ [2] https://ift.tt/zoj2kGF... [3] https://ift.tt/D7dlYJw [4] https://ift.tt/vn6BC8r [5] https://explore.ssp.sh https://ift.tt/lB8QxM9 August 3, 2026 at 01:12AM

Show HN: SteerPlane – Deterministic runtime guardrails for AI agents https://ift.tt/Zhf7mBa

Show HN: SteerPlane – Deterministic runtime guardrails for AI agents https://ift.tt/m1APHRM August 1, 2026 at 11:39PM

Show HN: Schema-backed, Git-based structured state for agentic systems https://ift.tt/8m72K3x

Show HN: Schema-backed, Git-based structured state for agentic systems I looked into how to store agentic state in a) a structured way that b) runs without any dedicated MCP memory/state servers and where I can get c) a clear diff-able audit trail of all state changes over time. Nothing that I could find fit the bill. In https://ift.tt/ceUJnx7 , I demo an implementation that fulfills these requirements by combining Claude agents with my previously published Commitspark library and its entirely Git-backed GraphQL API. In the demo, two independent Claude agents are simulated that contribute to a task tracker. A third agent reviews any task changes and rolls back obviously bad ones. A full demo transcript is included in the README, including the agents' raw tool calls. Task agent access to data happens via a small MCP server that exposes two Commitspark APIs (GraphQL API, schema API). These agents can then fetch the schema and author their own GraphQL calls, with GraphQL automatically enforcing written data is schema-conformant. The validator agent additionally has access to basic git functionality to view diffs and revert commits. I'm looking for feedback specifically on: whether schema validation on shared agent state is a problem people actually have, or whether loosely-typed JSON + retries is good enough in practice. July 31, 2026 at 11:50PM

Show HN: Tally – check a spreadsheet's numbers against their source, in-browser https://ift.tt/oNx5mSg

Show HN: Tally – check a spreadsheet's numbers against their source, in-browser https://ift.tt/jDXS2WG July 30, 2026 at 11:25PM

Show HN: Dreeve, a self-hosted dashboard for your sports and fitness data https://ift.tt/MNw5h2m

Show HN: Dreeve, a self-hosted dashboard for your sports and fitness data I've been building this for a few years under the name "Statistics for Strava" but I renamed it to Dreeve recently because of Strava's recently changed API usage terms. They paywalled their API. You point it at your activity files (FIT/TCX/GPX) or connect a Strava account, and it gives you a dashboard with segment efforts, gear and maintenance tracking, a heatmap, monthly calendar view, milestones and a year-in-review. It runs as a Docker container, stores everything in SQLite, and nothing leaves your machine. Stack is PHP 8.5 + Symfony, SQLite, Docker Compose. Simple, straightforward and fast. Caveats: it's built around a single user, so there's no multi-tenant story. The AI workout assistant is optional and off unless you configure it. Segment data still comes from Strava if you want it, which is the one dependency I haven't been able to remove. Docs at https://docs.dreeve.app . Happy to answer any questions you have https://ift.tt/jm8Sslt July 29, 2026 at 11:45PM

Show HN: Vyne – Zapier for DeFi users, run from any LLM or the workflow builder https://ift.tt/HclfReX

Show HN: Vyne – Zapier for DeFi users, run from any LLM or the workflow builder https://ift.tt/oXcZbWs July 29, 2026 at 02:31AM

Show HN: Verifiable receipts for firmware CVE reproduction https://ift.tt/swZXNA3

Show HN: Verifiable receipts for firmware CVE reproduction https://ift.tt/AraY2hx July 29, 2026 at 02:23AM

Show HN: Beakdown – a game inspired by Joust/Skirmish https://ift.tt/hQj3Amc

Show HN: Beakdown – a game inspired by Joust/Skirmish I used to play Joust with my little brother on the BBC Micro many moons ago and have fond memories of it. So when I was experimenting with Claude Opus 5 it was a nice inspiration for this game. Did a little research and found there aren't many games out there that just work in a browser without ads, loading screens or account sign-ups. So I've put this directly on the landing page with no noise in the way - it works on any browser on any device and loads instantly. If it doesn't work at all, please tell me. And also let me know if you think it needs music - I went without it to begin with but don't know if that's what people would prefer or not. Would also love to know how far you get, my personal best is 199,000. Thanks for your interest! https://beakdown.fun/ July 29, 2026 at 01:18AM

Show HN: Somebodyhire.me https://ift.tt/J1mfNT0

Show HN: Somebodyhire.me I originally had this as a personal resume site but decided to build it out into a platform where anyone can sign up and host a resume page. Once I build up the talent pool, I plan on marketing to hr depts and hiring managers. I just don't know a single person who's happy with hiring on either side right now and this feels like a better solution to me. https://ift.tt/nqlMHF1 July 28, 2026 at 09:48PM

Show HN: A 538-style dashboard for upcoming Knesset elections https://ift.tt/yTsURGB

Show HN: A 538-style dashboard for upcoming Knesset elections https://ift.tt/A6PHQvU July 28, 2026 at 12:34AM

Show HN: Let's Seal – Let's Encrypt for document signing, free and self-hosted https://ift.tt/kXvURxh

Show HN: Let's Seal – Let's Encrypt for document signing, free and self-hosted TLDR, Let's Seal gives the finger to Adobe and every doc signing tool (docusign, google, etc) who pay to play with the Adobe Approved Trust List and then charge you for something that should be free. Currently even the person checking if a document/contract is sealed or code is authentic has to also be inside the same Adobe walled garden too. Verification, the part that should be free is the part everyone charges for. Thats the shape Let's Encrypt fixed for TLS, and I wanted the same thing for documents and files. The core idea therefore needed to go a bit beyond e signatures and i created an open standard (SEAL), plus free tools that implement it. When you seal a file, three independent things happen. 1. it gets a signature from a certificate authority, chaining to a public root. 2. its record is appended to an RFC 6962 transparency log. and 3. its SHA256 is timestamped on a public blockchain (Bitcoin) via OpenTimestamps. Those three give you integrity, transparency and a timestamped proof. And importantly, none of those depend on Let's Seal and none are gated. You can verify with the tools you already have, no Let's Seal account and no Let's Seal software. A sealed PDF carries a standard PAdES signature, so any PDF reader validates it. A sealed build artefact carries a cosign compatible signature and a SLSA provenance attestation. The Bitcoin timestamp verifies with stock ots. 3 ways to use it. 1. The free web app. We kindly have backing from Backblaze to cover storage costs for the foreseeable. So you can upload or issue any number of documents, get a public proof page at /d/ and verify it at https://ift.tt/nzhEkOJ for free. Multiple accounts, multiple seats, enterprise functions. Free. 2. Self host the whole thing. Apache-2.0, one Next.js app plus a signing service that holds the CA key on localhost. Storage is any S3-compatible bucket or local disk. If you'd rather run your own root of trust, you can. 3. Programmatically. via the CLI and a hosted API. This is the Let's Encrypt/certbot angle. Seal or anchor things from CI, or have a backend seal every invoice or report as its generated. The CLI is sealbot. It runs anywhere Node runs (npx sealbot) and there are native binaries for macOS, Linux and Windows with no runtime needed. Theres a GitHub Action wrapping the same tool, so a release workflow can seal its own artifacts. Its what proves our own releases. KYC is semi-handled (to a degree) it's hard to do for free (at least for now), but issuers (your companies or websites) domains can be authenticated with a DNS record added, which proves the issuer has control over a domain. Sign-in can be authenticated to an email via Google Sign in and a few others will be added to the web app in time (Same as Docusign currently). Ideas welcome on future KYC should there be a demand. Feedback welcome on the standard (SPEC.md in the repo). Repo: https://ift.tt/lSJ3LXt Site: letsseal.org Thx https://ift.tt/lSJ3LXt July 27, 2026 at 09:22PM

Show HN: An interactive way to exploit an LLM without going to jail https://ift.tt/z7xp2sW

Show HN: An interactive way to exploit an LLM without going to jail https://ift.tt/tIR0V6s July 26, 2026 at 11:46PM

Show HN: Proxmox -> Share your host's Bluetooth with a VM over the network https://ift.tt/VzYcgNy

Show HN: Proxmox -> Share your host's Bluetooth with a VM over the network https://ift.tt/X9NyAZh July 26, 2026 at 01:11AM

Show HN: I made some transistor animations https://ift.tt/MIDT56e

Show HN: I made some transistor animations Hi HN, I made some animations of the most important kinds of transistors using my semiconductor simulation, details of which are on the page. I tried to make the visuals as realistic as possible while also aiming for clarity. If you want to go beyond the charge carriers and look at, for example, the electric field, you can do so in the simulation software. The desktop software also has less common devices like IBGTs and SCRs that have similar animations. The last thread about my software was posted here about a year ago: https://ift.tt/yfvs2qm https://ift.tt/P1XqiGN July 25, 2026 at 12:07AM

Show HN: PBasic is a modern BASIC interpreter with a retro vibe https://ift.tt/v3MWXZ2

Show HN: PBasic is a modern BASIC interpreter with a retro vibe pBasic is a modern BASIC interpreter with a retro vibe. It allows you to easily find your way into computer programming and form a connection with the code. You will learn about Games programming, how to animate Sprites, and compose your own Functions. pBasic gives you a blank canvas in which you can realize your own creations. https://ift.tt/jCmblE0 July 24, 2026 at 10:30PM

Show HN: A representation of a chapter of your life through music https://ift.tt/oiaL6ep

Show HN: A representation of a chapter of your life through music https://www.cuecard.live July 24, 2026 at 11:22PM

Show HN: Advanced Coffee Search Covering Over 17,000 coffees https://ift.tt/4FHBrYj

Show HN: Advanced Coffee Search Covering Over 17,000 coffees https://ift.tt/ZiQGjlT July 24, 2026 at 02:59AM

Show HN: Trifle – Open-source analytics that stores answers, not events https://ift.tt/8pnPqO0

Show HN: Trifle – Open-source analytics that stores answers, not events Trifle is an open-source time-series analytics library that aggregates nested counters instead of storing raw events. All in the database you already have. After rebuilding it twice over 10 years, it now tracks ~1B events a day at my day job. It started in 2015 as my own Rails APM. I plugged into ActiveSupport::Notifications, got a few small users, and one bigger one whose scraping app broke everything. That sparked the core idea: aggregate counters into pre-defined time buckets, so a single write increments multiple buckets at once. The APM eventually faded away without much traction. Later in 2021 I needed analytics at my day job. Instead of going for something out there I revised the idea of Trifle as a more generic analytics library, borrowing some data warehouse ideas. First used Redis, then Postgres, eventually MongoDB. Hence why Trifle::Stats comes with multiple drivers that keep the DSL unified while storage layer changes with your needs. In our case (huge write volume, some reads) PG read faster but slowed on large writes. The nested values are the whole trick here. Single: Trifle::Stats.track( key: 'requests::aws::s3_uploads', values: { count: 1, status: { request.response_code => 1 }, size: payload.bytes, duration: { sum: request.duration, count: 1 } } ) builds up counts for requests, success rate, result status codes, duration for multiple time buckets at once. Single bucket from 2am then looks like: { count: 14, status: { 200: 12, 500: 2 }, size: 5628341, duration: { sum: 43, count: 14 } } If request.duration is in seconds, then sum stored under duration would be in seconds as well. Success rate is never stored, but it is calculated by dividing 200s over total number of requests. Same with average duration: sum over count. You ask for a metrics key, granularity and timeframe and you get back aggregated values at each point. Ready for charts or to answer "Average response time over last 30 days". There's a Series wrapper for aggregating and formatting values for charts in a simple call. And as building dashboards is not as much fun for other devs as I thought, I built Trifle App - a visual layer with dashboards, scheduled digests and alerts. It's written in Elixir, so I ported the library to Elixir too. And later to Go for a CLI. All three are compatible, write in one and read in another. Today we track activity from over 100M background jobs a day which turns into about 1B events. It runs surprisingly cheap when you're willing to trade some safety away (turn off journaling and write concerns in Mongo). 3-node Hetzner MongoDB cluster where the primary does 20% utilization costs us around $1k/month. It has its limitations. Payloads can't hold tens of thousands of keys. Documents becomes too large to update efficiently. Some planning ahead is needed. And then there are no dimensions. Sometimes you can nest them (country - there are only so many countries), sometimes it's better to have dedicated metrics key per dimension (customer - growing forever). That multiplies tracked events, hence 1B events from 100M jobs. The libraries are MIT. The App is source-available under ELv2 - free to self-host and paid cloud if you want it managed. I build this on the side with no investor money to burn on a free service. Happy to answer anything about architecture, storage models, my failures or why I didn't give up on this yet. https://trifle.io/ July 22, 2026 at 08:09PM

Show HN: Szr: A safer command output reduction for coding agents https://ift.tt/kZCXwKn

Show HN: Szr: A safer command output reduction for coding agents https://ift.tt/05VDMA1 July 22, 2026 at 11:33PM

Show HN: Onus – self-hostable vuln scanner combining 8 tools into one report https://ift.tt/FR19y8H

Show HN: Onus – self-hostable vuln scanner combining 8 tools into one report https://ift.tt/3mL7kr9 July 22, 2026 at 10:24PM

Show HN: Edky, a CLI to convert Ed25519 public keys from one encoding to another https://ift.tt/7TVLscf

Show HN: Edky, a CLI to convert Ed25519 public keys from one encoding to another Everything increasingly runs on Ed25519 keypairs, but Ed25519 public keys can be encoded as text in dozens of surface-incompatible different ways: hexadecimal, Base64 (OpenSSH), Base32z (iroh, pkdns), Base58 (NEAR), and Multibase (IPFS, libp2p), just for starters. Edky is a command-line tool and Rust library that converts between these Ed25519 surface encodings, aiding use of the same underlying keypair across e.g. an iroh endpoint, a libp2p peer, or a NEAR Protocol account. (Surprisingly, a conversion utility like this didn't yet exist!) $ cargo binstall -y edky $ edky convert -f iroh -t libp2p 47pjoycnsrfmxikm95jh13y88e8qnhzu5kungjpxyepgt7a8krpy z6MktwupdmLXVVqTzCw4i46r4uGyosGXRnR3XjN4Zq7oMMsw $ edky convert -f libp2p -t iroh z6MktwupdmLXVVqTzCw4i46r4uGyosGXRnR3XjN4Zq7oMMsw 47pjoycnsrfmxikm95jh13y88e8qnhzu5kungjpxyepgt7a8krpy $ edky convert -f near -t hex ed25519:FVen3X669xLzsi6N2V91DoiyzHzg1uAgqiT8jZ9nS96Z d75a980182b10ab7d54bfed3c964073a0ee172f3daa62325af021a68f707511a $ edky convert -f hex -t near d75a980182b10ab7d54bfed3c964073a0ee172f3daa62325af021a68f707511a ed25519:FVen3X669xLzsi6N2V91DoiyzHzg1uAgqiT8jZ9nS96Z https://ift.tt/krQSpGa July 21, 2026 at 11:39PM

Show HN: Neuron. Turn a SQL query history into a semantic layer https://ift.tt/EJ6KqhW

Show HN: Neuron. Turn a SQL query history into a semantic layer My cofounder and I previously ran analytics groups in life sciences. That means we led teams of analysts who typed SQL all day long and we ran into common issues of consistency, correctness, and knowledge transfer. We were always one resignation away from losing all of the history on a project or a client. When we left that world we thought we could solve the problem with auto-documentation. Cut to now and we've landed on the modern version of that solution, which is to turn previously executed queries into context for AI. The intuition is roughly this: a smart analyst can read SQL and have a pretty good idea of what's going on, and in fact can infer a lot of institutional knowledge about the domain and how to analyze particular data. LLMs are not great at this (Anthropic and Snowflake have written as much). So we act as the "smart analyst" to pull out institutional knowledge and practices (in the form of SQL) that you can give to an LLM so that it can code like a competent analyst on your team. Right now we're deploying it as a semantic layer population tool. You want to fill up a Genie or Cortex semantic layer? Run our code on your query history, prune it with your experts (delete this, rename that, etc.), and get moving. That can take hours/days instead of weeks. Plus, everything we export is portable to whatever system you choose. FYI we ask for emails on the free trial download so we can monitor our traction and build our network but you don't need to include it if you don't want to. We're hungry for feedback from people who work in the field and are facing these challenges. Major, major thanks in advance for your time. https://ift.tt/tC76ZEl July 20, 2026 at 11:41PM

Show HN: A gallery of browser-based PDF imposition and printing templates https://ift.tt/iRVrcuX

Show HN: A gallery of browser-based PDF imposition and printing templates https://ift.tt/0pizquJ July 19, 2026 at 11:16PM

Show HN: Chalie – AI peer not employee https://ift.tt/E0wY1Jo

Show HN: Chalie – AI peer not employee https://ift.tt/iBwy03z July 20, 2026 at 01:04AM

Show HN: Bribes.fyi – Built something to report bribes https://ift.tt/loeLEDf

Show HN: Bribes.fyi – Built something to report bribes https://bribes.fyi/ July 19, 2026 at 09:01PM

Show HN: Ilya Sutskever's AI reading list into a learning RPG – using kimi k3 https://ift.tt/oS7kIdc

Show HN: Ilya Sutskever's AI reading list into a learning RPG – using kimi k3 I wanted to take kimi k3 for a spin. It turned my simple one sentence prompt to this. Repo here. https://ift.tt/kmT7bNp Well, I'm mindblown. Very humbling for me as a software engineer. Took couple hours for it to build this completely autonomously. And it was all from its mobile app. It couldn't render this though from within the app - it does have a feature to preview any website and publish it on kimi's domain - but it didn't work for this. I had to put it on github pages. It doesn't store anything btw - all progress is tracked in your browser storage. https://ift.tt/29vAF3s July 19, 2026 at 04:24AM

Show HN: RewindCup – explore 23 World Cups on an interactive globe https://ift.tt/DgHjixE

Show HN: RewindCup – explore 23 World Cups on an interactive globe https://rewindcup.com July 19, 2026 at 03:37AM

Show HN: Peek-CLI: Let Claude Code iterate on front end designs https://ift.tt/wD7A6Xy

Show HN: Peek-CLI: Let Claude Code iterate on front end designs https://ift.tt/A6bdolx July 19, 2026 at 12:32AM

Show HN: SDF Pelicans on Bicycle https://ift.tt/187YFOx

Show HN: SDF Pelicans on Bicycle https://ift.tt/liCwALr July 19, 2026 at 12:47AM

Show HN: Tools Berry – client-side calculators with open-source tax engines https://ift.tt/KjuGprP

Show HN: Tools Berry – client-side calculators with open-source tax engines https://ift.tt/J23TfUX July 18, 2026 at 01:08AM

Show HN: Lific: Issue trackers should be simple, right? https://ift.tt/vXMV3gp

Show HN: Lific: Issue trackers should be simple, right? I built Lific because I direct AI coding agents on largish projects and needed somewhere for project state to live that isn't markdown files in the repo. When I was begging to work on long horizon ideas, I started on Linear, but my agent files issues faster than a human does, and I hit their limits and pricing wall almost immediately. Then I self-hosted a popular open source tracker which meant running its 13 containers, and its MCP integration was 30k tokens and I got so fed up that I eventually removed it and went back to .md files for a few weeks. Lific is the opposite shape of most of your self hosted server issue trackers: It's a single Rust binary that uses SQLite, and it has an optimized MCP server built in. Web UI is also included integrated directly into the binary. The simplicity is meant to only apply to the size and the ease of installation. The web UI is fully fleshed out with all of the UX you would expect from an issue tracker like linear. Since I started using lific, my agent flow is that I open the web UI, find a few issues I want to work on, then tell the agent "work on LIF-298, 299 and 301, and if you find bugs, file them as new issues." At the end of the day the project has tracked itself. Issues have statuses, blockers, and comment threads, so "what's workable right now" is a query instead of the agent guessing. Plans are persisted step trees, so a session tomorrow resumes with the same understanding of the goal and the path as the session that made the plan. My largest project has 300+ issues and 100+ docs and agents search it fast. Everything exports to markdown in one click, and the database is just a file on your machine. Setup is ` cargo install ` ` lific init ` ` lific connect ` then pick your harness (OpenCode, Cursor, Claude Code, etc). One honest caveat: on Windows there's no service install yet, so the binary has to be actively running for MCP or Web UI to work on windows. The biggest reason I think Lific is different than a lot of the other options is the lightweight nature of it alongside still having a fully featured web UI. It's meant for self hosters to work on big projects with agents, without sacrificing the other benefits of an issue tracker like a nice management UI or authentication for teams using it. Would genuinely love feedback and bug reports either here or on the discord! https://lific.dev July 17, 2026 at 11:22PM

Show HN: Rudo - A small, elegant dock for Wayland https://ift.tt/BDuXye0

Show HN: Rudo - A small, elegant dock for Wayland https://ift.tt/Jnik7oG July 17, 2026 at 01:12AM

Show HN: Tree, truth, druid, dryad, and tar share one Proto-Indo-European root https://ift.tt/NfSJZhF

Show HN: Tree, truth, druid, dryad, and tar share one Proto-Indo-European root https://ift.tt/cegJMHA July 16, 2026 at 11:11PM

Show HN: SirixDB 1.0 Beta – Git-Like Versioning, Diffs, Time-Travel Queries https://ift.tt/f7dBJF2

Show HN: SirixDB 1.0 Beta – Git-Like Versioning, Diffs, Time-Travel Queries Hi HN! I've posted SirixDB here before, back in 2019 ( https://ift.tt/sd9Mrvh ) and again in 2023 ( https://ift.tt/M9IjZ0G ). The core idea behind SirixDB is, that history is a first-class citizen. Every commit stores a lightweight, queryable revision. You can query any point in time, even individual nodes (for instance JSON values), diff arbitrary revisions, and efficiently track how data evolved without replaying events. Unlike traditional event stores, historical states do not need to be reconstructed by replaying events nor do we have to think about projections. Revisions are directly queryable. A simple example: Jan 1: Record "Price = $100, valid from Jan 1". Stored on Jan 1 (transaction time). Jan 20: Discover price was actually $95 on Jan 1. Commit correction. After correction, you can ask across both axes: - "What did we THINK the price was on Jan 16?" -> $100 (Transaction time) - "What WAS the price on Jan 1?" -> $95 (Valid time) I've worked on this in my spare time since 2013, following its academic precursor (Idefix/Treetank) at the University of Konstanz. The architecture relies on an append-only physical log and a persistent copy-on-write page trie. A high level view of the architecture: Physical Log (append-only, sequential writes) ┌────────────────────────────────────────────────────────────────────────┐ │ [R1:Root] [R1:P1] [R1:P2] [R2:Root] [R2:P1'] [R3:Root] [R3:P2'] ... │ └────────────────────────────────────────────────────────────────────────┘ t=0 t=1 t=2 t=3 t=4 t=5 t=6 → time Each revision is indexed, and unchanged pages are shared: [Rev 1] [Rev 2] [Rev 3] │ │ │ ▼ ▼ ▼ [Root₁] [Root₂] [Root₃] │ │ │ │ │ │ │ └─────────┐ │ └────────┐ │ └─────────┐ ▼ ▼ ▼ ▼ ▼ ▼ ┌──────┐ ┌──────┐ ┌──────┐ ┌──────┐ │ P1 │ │ P2 │ │ P1' │ │ P2' │ └──────┘ └──────┘ └──────┘ └──────┘ Rev 1 Rev 1+2 Rev 2+3 Rev 3 (shared) (shared) Beneath the root pages sit node and secondary indexes, using a novel sliding-snapshot algorithm to balance read/write performance. Everything is queryable using JSONiq via the Brackit compiler. Back in 2019, and even in 2023, SirixDB was very slow due to GC pressure. Unlike most other document stores, SirixDB stores fine-grained nodes, and I came to realize that an on-heap (JVM) representation made up of lots of small objects simply didn't make sense. I measured it with async-profiler — with some help from Andrei Pangin himself — and the result was that the poor throughput was due to the sheer amount of allocations which scaled almost linearly with the number of open transactions. Working a full-time software engineering job, I lacked the energy for a massive spare-time rewrite. About a year ago, I started experimenting with AI. It turned out to be ideal for automating the tedious, repetitive parts of migrating the storage layer to Java's Foreign Function & Memory API, storing pages completely off-heap. Looking further ahead, the append-only, immutable-page design maps naturally onto object storage like S3 and distributed logs like Kafka for a cloud version, and initial prototypes already exist. Maybe that becomes a commercial service one day, but for now, I'm just thrilled to see these core design principles finally proven out.There's an interactive demo, documentation, and the code is on GitHub. I'd love feedback and am happy to answer questions! kind regards Johannes [1] https://sirix.io | https://ift.tt/KOCgxSv [2] https://ift.tt/RGJQ0Bn [3] https://demo.sirix.io [4] https://sirix.io/docs/ [5] http://brackit.io https://ift.tt/KOCgxSv July 15, 2026 at 09:16PM

Show HN: Leet Robotics: Learn robotics and ROS2 with hands-on courses https://ift.tt/rAZ5WDq

Show HN: Leet Robotics: Learn robotics and ROS2 with hands-on courses Hi all, I've just launched Leet Robotics: a platform to learn robotics hands-on, with a full ROS2 workspace that runs in the browser (Jazzy, Gazebo Harmonic, Foxglove, VS Code) - no install required. The platform also has room for sharing projects and simulation assets as it grows. Our first course is live now: Intro to ROS2 (free to read). The course teaches skills ranging from building your first node to a capstone project of a robot touring a museum world, with every lesson runnable in the online workspace (free accounts get an hour of workspace time daily - enough to follow the course). Would love feedback from this community: on the course, the workspace experience, and what courses to build next. https://ift.tt/vSqxdnz July 15, 2026 at 05:44PM

Show HN: Beautiful Type Erasure with C++26 Reflection https://ift.tt/snjTVE2

Show HN: Beautiful Type Erasure with C++26 Reflection Try it on Compiler Explorer: https://ift.tt/ZVJdl0a Check out the source code: https://ift.tt/wuaLFt4 https://ryanjk5.github.io/posts/rjk-duck/ July 14, 2026 at 06:10PM

Show HN: Find Remote Accounting Jobs https://ift.tt/V8cden0

Show HN: Find Remote Accounting Jobs https://ift.tt/qZz1oNg July 13, 2026 at 11:47PM

Show HN: Scramble Quest https://ift.tt/UdhOgGe

Show HN: Scramble Quest https://ift.tt/UHSfy80 July 12, 2026 at 11:28PM

Show HN: Sqlsure – deterministic semantic checks for AI-generated SQL https://ift.tt/sYeTAKt

Show HN: Sqlsure – deterministic semantic checks for AI-generated SQL https://ift.tt/bKHXwPc July 12, 2026 at 01:33AM

Show HN: Don't let your engineering brain rot in the age of AI https://ift.tt/gqL9JiM

Show HN: Don't let your engineering brain rot in the age of AI https://ift.tt/VfSz0RK July 12, 2026 at 01:27AM

Show HN: Share and explore custom Claude Code status lines https://ift.tt/5sve4uO

Show HN: Share and explore custom Claude Code status lines Hey HN, I made a registry for claude code users to share and explore status lines. I found that my friends/coworkers and I would always share screenshots of our terminal to show off our custom claude lines so I decided to build this registry as a place for others to show off! https://claudelines.com July 12, 2026 at 01:21AM

Show HN: We beat Cloudflare's bot detection (open-source stealth browser) https://ift.tt/YyDUmBQ

Show HN: We beat Cloudflare's bot detection (open-source stealth browser) https://ift.tt/4z3Jcjq July 11, 2026 at 05:56AM

Show HN: SubjectiveZero, an open-source agentic node editor for creative coding https://ift.tt/mr3N0GZ

Show HN: SubjectiveZero, an open-source agentic node editor for creative coding Hey there, My name is Clem, I've been a solo indie dev for a couple years now, exploring frontier tech like XR and agentic workflows in the context of creative / interactive work. I've been building creation tools for a while and some common design challenge is to figure out the right level of abstraction for your tool. You can always make it super advanced and complex with low level concepts (shader composition, actual code etc.) but then you get something with a high complexity / learning curve. On the other hand, if you make your tool too high level, it might be easier to use at first, but people will most likely hit a wall eventually and start fighting with your tool to get their edge case done (you see that on mobile a lot actually). With this prototype (called SubjectiveZero), I'd like to imagine that we can kind of move the "slider" on the abstraction layer, meaning that you can actually start with prompts that describe the goal, and you can go as high level (stay with abstract prompts) or low level as you'd like (more specific prompts, or even edit the generated code directly)! The agent orchestration actually understand your context and work along side with you to figure out what could be the best node graph structure for your project (that and some fun little procedural UI done at the node level). If i had to pitch it in 30 seconds, I'd say "Think TouchDesigner and friends but with agent orchestration". When you use it, it will generate real native code (Swift/Metal for now) that you can actually hot reload and iterate on either manually or through agents. It's still an early prototype and macOS only for now, but I'd love to get genuine feedback that could help me drive where this project should go next (or not). Lastly, I'm absolutely open and upfront on the fact that I used agentic coding for this, but as people say: "kept on a short leash". The architecture and specs were relatively well thought out and I personally prefer to be in the loop and review all the code being written to make sure it's going in the right direction. Oh and it's open source :-) Hope you like it! https://ift.tt/Ks2GPwz https://ift.tt/Ks2GPwz July 10, 2026 at 08:53PM

Show HN: Wyrm – Solve algebra by touch, built on an open-source soundness engine https://ift.tt/c39dMLX

Show HN: Wyrm – Solve algebra by touch, built on an open-source soundness engine There is a mobile game called DragonBox. It sort of tricks you into learning algebra by starting with very abstract manipulations of a puzzle that must follow rules... gradually the game teaches you more and more rules and also strips out the more abstract elements until on the last levels you are finally solving real equations. I loved it, it taught my kids algebra.... and it was just fun. Over the years I often thought that there should be a calculator for Algebra that works this way... something where you can drag terms around and cancel & distribute with gestures, but most importantly enter your own problems. It should also do more kinds of problems than DragonBox allowed. So I finally decided to build it. https://dicroce.github.io/wyrm/home.html Here's a video showing it: https://www.youtube.com/watch?v=_STbS4zvIlU . If you'd rather just play with it: there's a limited in-browser demo (real engine, a few example equations, no download) on the landing page — https://dicroce.github.io/wyrm/home.html . The app can be found on iOS ( https://ift.tt/5CI1tEG ) and as of this week on Google Play ( https://ift.tt/0H7RAm2... ). I also decided to open source the underlying math engine so others could build on it: https://ift.tt/P1iHdqQ . My goal for the engine btw is to build it all the way up to Calculus. Monetization is deliberately boring: the engine is free (MIT), and the polished gesture app is $4.99 once. No subscriptions, ads, accounts, or analytics. I'd love feedback on the engine design — especially from anyone who's worked on CAS or proof-assistant-adjacent problems. And if you played DragonBox as a kid and wished it went further: this is for you! https://ift.tt/P1iHdqQ July 9, 2026 at 04:46PM

Show HN: Real-time n-body tree code in CUDA https://ift.tt/wuI09sD

Show HN: Real-time n-body tree code in CUDA Sharing an old project of mine, on my RTX 500 Ada laptop GPU, it can simulate up to 4 million particles at ~400 ms per step using the Barnes-Hut algorithm, saturating the 4GB of VRAM available. The octree construction is fast, as well as the traversal. The major bottlenecks are the VRAM usage (1 million bodies require ~1GB), which could be probably halved by reusing intermediate buffers, and the particle to leaf evaluation, which would benefit from more fp32 FLOPS. Moreover, I still don't have a good heuristic to predetermine the size of the BFS queue, perhaps some sort of memory paging could solve the issue. https://ift.tt/V5k6CwM July 10, 2026 at 09:17PM

Show HN: Getting GLM 5.2 running on my slow computer https://ift.tt/wUr2mso

Show HN: Getting GLM 5.2 running on my slow computer The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context. How it responds in int4 and whether the quality is maintained or not. Until I got to the point, on my computer with 32GB of RAM, I was able to communicate with GLM 5.2 with times that, of course, aren't high in cold start, but even then, we're talking about 0.1 tok/s, but that wasn't important to me. The important thing was the journey to reach this goal and, above all, changing the perspective on the project. I wanted it to work at all costs, even slowly. So I created Colibrì, which was born from a very simple idea, to be honest, but tested in every way, where a 744B Mixture-of-Experts model activates only ~40B parameters per token—and only ~11 GB of those change from token to token (the routed experts). So: The dense part (attention, shared experts, embeddings—~17B params) stays resident in RAM at int4 (~9.9 GB); The 21,504 routed experts (75 MoE layers × 256 experts + the MTP head, ~19 MB each at int4) live on disk (~370 GB) and are streamed on demand, with a per-layer LRU cache, an optional pinned hot-store, and the OS page cache as a free L2. The engine is a single C file (c/glm.c, ~1,300 lines) plus small headers. No BLAS, no Python at runtime, no GPU.No GPU or serious hardware because I don't have that hardware so I can't test it on hardware that is more powerful than my computer.Colibrì is a one-person project, written and tested entirely on a 12-core laptop with 25 GB of RAM — the numbers above are the ceiling of what I can measure at home. Any feedback is welcome! Repo: https://ift.tt/bQ8Xi2v https://ift.tt/bQ8Xi2v July 9, 2026 at 01:35PM

Show HN: Codex Explorer, a local session manager for Codex CLI https://ift.tt/G6Vp92a

Show HN: Codex Explorer, a local session manager for Codex CLI https://ift.tt/zpRKMbi July 9, 2026 at 11:53PM

Show HN: Onboard-CLI, a LLM powered and AST-based tool to visualize codebase https://ift.tt/CNG9Kda

Show HN: Onboard-CLI, a LLM powered and AST-based tool to visualize codebase https://ift.tt/UEXyNsS July 9, 2026 at 01:39AM

Show HN: Skill-extractor turns coding agent transcripts into reusable skills https://ift.tt/JtLaQHI

Show HN: Skill-extractor turns coding agent transcripts into reusable skills https://ift.tt/HK7fx4M July 9, 2026 at 01:33AM

Show HN: REST - Living Without Burnout. A manifesto about sustainable discipline https://ift.tt/lW7iT84

Show HN: REST - Living Without Burnout. A manifesto about sustainable discipline Lately, I’ve been thinking a lot about what gives me energy and what slowly takes it away. Those thoughts eventually turned into a small manifesto I called REST. https://themanifesto.rest/ July 9, 2026 at 01:12AM

Show HN: Hnwork.app – UI for Who is hiring posts https://ift.tt/lALUxfZ

Show HN: Hnwork.app – UI for Who is hiring posts Hey HN, I built a UI on top of the "Who is hiring" posts. Take a look at https://hnwork.app ! One of the downsides of unstructured text posts is the readability due to it being free-form and having little to no format. While there are other tools that have been built over the years to make perusing Who is hiring posts easier, I took a try on making my own (I actually tried to build this at a YC hackathon a few years back, but got around to completing it recently). Features: - Text search and search filters - Original post text with call outs to important information - Removes posts that aren’t on topic (complaints, seeking work, vague or missing contact info) - Analytics - API In addition, job posters can create accounts to submit postings through the app. While I don’t expect posting to move over to this app, it’s what I envisioned what a Who is hiring thread would like as an app: - Structured postings with required fields (e.g., salary range required) - Job posters get notifications about comments on their posts - Job posters get verified through their email before posting (e.g., someone posting a Sony job has a Sony email address) - Companies with multiple job posters can coordinate postings and view past postings - Admins can audit and approve companies and posts Job seekers can also create an account to post comments or get access to a simple API but otherwise browsing doesn’t require any kind of signup/signin. I’m open to feedback: let me know if you’d like me to ingest more data from past months, something is missing or broken, or there’s a new feature you’d like to see. Thanks! https://hnwork.app/ July 9, 2026 at 01:30AM

Show HN: Fork – Let users build features on top of existing applications https://ift.tt/Qbe3KUN

Show HN: Fork – Let users build features on top of existing applications Our initial release is a Chrome extension that builds on top of Gmail and Google Calendar. We keep limited trace activity of coding sessions for 30 days to troubleshoot and improve our offering. No data (events, emails) from Google is ever logged or retained. 50 second demo: https://www.youtube.com/watch?v=JQ292bncO_c Chrome extension (free + no login): https://ift.tt/GBlcWA4... We have a lot to learn and build. Would love any and all feedback! Paul & Dalton https://withfork.co/ July 7, 2026 at 11:47PM

Show HN: Record, replay, and improve AI agents in production https://ift.tt/DgRMn3C

Show HN: Record, replay, and improve AI agents in production At the AI Engineering World's Fair a big part of the conversation was to nail the self improvement loop. Our take on this is to record state of the agent execution with a durable runtime, then allow users to replay from state checkpoints and run 'what-if' experiments. It's OSS and free to use. Would love some feedback from the community. https://ift.tt/dKjtxMD July 6, 2026 at 10:56PM

Show HN: Handoff – a verified context bridge between Claude Code sessions https://ift.tt/5JoXiBI

Show HN: Handoff – a verified context bridge between Claude Code sessions https://ift.tt/ozrv3eP July 5, 2026 at 10:48PM

Show HN: I built an encrypted BLE dongle for pasting stuff to air-gapped devices https://ift.tt/V8miX0g

Show HN: I built an encrypted BLE dongle for pasting stuff to air-gapped devices Definitely one of those "20 minute adventure gone wrong" projects where all I wanted initially was a quick wireless rubber ducky for bitlocker keys and the like and then I kept adding stuff like AES-256..... Currently working on adding WebAuthn/FIDO support because the hardware is already there and scope creep is a lifestyle at this point. Would love feedback, especially on the security side. Repo and PCB files are fully open source. https://ift.tt/tB3ZcD6 July 5, 2026 at 02:43AM

Show HN: Gemma 3 inference in pure C++ with Metal acceleration https://ift.tt/OLeSf1w

Show HN: Gemma 3 inference in pure C++ with Metal acceleration https://ift.tt/kHWniYq July 4, 2026 at 09:24PM

Show HN: Opbox – CRDT based sync for text files on disk https://ift.tt/TEKAXHI

Show HN: Opbox – CRDT based sync for text files on disk Hi! I’m one of the founders of s2.dev, and recently have been hacking on opbox, which is an open-source daemon that turns directories of text files (code, markdown, etc) into collaborative, multi-player workspaces. This started as a bit of an intellectual curiosity, to see if it was possible to do real-time sync at the filesystem level (i.e., in an editor-agnostic way). The idea is pretty simple: - Opbox workspaces are roughly analogous to git repositories (and can be used alongside existing git repos, to share live changes between commits) - When the opbox daemon is running in a workspace (ob start), it listens for local filesystem events within its directory (writes, deletes, new files), and translates them into operations (the titular “op”) on shadow CRDT documents (Yrs) corresponding to each text file (as well as one doc for the namespace as a whole, which handles paths) - These shadow CRDT docs are maintained in a workspace-local sqlite db (Turso) - The ops, which represent diffs on a corresponding CRDT document, are then appended to a durable stream (S2) that acts as a shared journal for all sync participants - Opbox also reads from that journal, receiving ops from other participants, which are then used to update the local documents, first in the db, then by materializing them into actual files on disk This has worked surprisingly well for sharing things like Obsidian graphs in real-time. It’s most helpful in cases where you want the ability to edit local files from arbitrary editors, but still collaborate live. The experience is best from editors where you can configure an aggressive autosave policy, and where edits to an open file are reflected in the editor in a timely way. To gain confidence in the correctness of the core opbox flows (particularly all the nuances around bidirectional sync) I invested in wiring up deterministic simulation testing using the turmoil library, which has been incredibly helpful (see the opbox-sim crate in the repo). https://www.opbox.dev/ July 4, 2026 at 12:26AM

Show HN: Auto-continue Claude Fable 5 the second your 5-hour limit lifts https://ift.tt/miNvqK6

Show HN: Auto-continue Claude Fable 5 the second your 5-hour limit lifts https://ift.tt/PXD371k July 4, 2026 at 01:05AM

Show HN: Dockside – I turned unused space around the macOS Dock into a workspace https://ift.tt/eUv4Vl8

Show HN: Dockside – I turned unused space around the macOS Dock into a workspace https://ift.tt/nXKj0c4 July 3, 2026 at 11:35PM

Show HN: Piggy – lazy senior dev mode for AI agents (80–94% less code) https://ift.tt/NnjstZG

Show HN: Piggy – lazy senior dev mode for AI agents (80–94% less code) https://ift.tt/bi3PHOK July 3, 2026 at 12:59AM

Show HN: A provider-agnostic agent loop built on ports and adapters https://ift.tt/SkjxNKF

Show HN: A provider-agnostic agent loop built on ports and adapters I work on agent infra at Featherless. This is MIT and works with any OpenAI-compatible endpoint, not just ours. I kept rebuilding the same loop: call model, run tools, feed results back, stop. Every framework I tried either owned the UI, owned the control flow, or dragged a dependency tree. So I pulled the loop out and put every piece behind an interface: memory, model, tools, stop condition. The loop depends only on the interfaces. It never writes to a screen. It emits one typed event stream, so a trace is just data, and you render it however you want. The landing page scrubs one run and rebuilds a CLI, a DOM timeline, and raw JSONL from the same stream. One dependency (zod). Same build runs in Node, Bun, Deno, and a browser tab. Every seam is tested in isolation with deterministic doubles, no network. Why not the Vercel AI SDK, pi, or LangGraph: AI SDK owns more of the surface and has been awkward with self-hosted tool calling. pi is a great coding-agent toolkit but it's shaped around being a coding agent and ships a TUI. LangGraph is a heavier graph framework. This is the layer under all of those: the bare loop you'd build any of them on. Happy to be told where the seams are wrong. If anyone finds any problems let me know this field moves at break neck speed so let me know if I am missing anything. https://ift.tt/6hECm2k July 3, 2026 at 12:52AM

Show HN: Inkwell – An RSS reader for e-ink devices https://ift.tt/TCNyu5j

Show HN: Inkwell – An RSS reader for e-ink devices https://ift.tt/DHSyVBX July 2, 2026 at 09:08PM

Show HN: ctx – Search the coding agent history already on your machine https://ift.tt/FGkAil5

Show HN: ctx – Search the coding agent history already on your machine Coding agents don't have long-term memory. But you do have months of full-fidelity agent transcripts stored on your machine. A simple solution that goes a long way: ingest those transcripts and logs into a structured SQLite database, then search them with ranked text match. Everything is fully local and doesn't require anything fancy like a graph database or hosted memory service. This is the idea behind ctx, a Rust CLI that handles the ingestion and searching. We give our agents a skill that tells them to reference past sessions before working in an area. Usually we do this through an "Agent History Research Subagent" whose job is just to prepare a short brief covering any relevant history before the task begins. A real example: sometimes our test suite runs would fail because disk was full on the runner. The correct approach was to run the cleanup runbook, but the root cause of the failure was not clear to the agents, so they would think it was a test regression and go down the wrong rabbit hole debugging. When the agent searched history, it realized this failure had been encountered before and found the right workaround immediately. That got the agent onto the right cleanup path, and later we improved the log output so the same failure would be clearer next time. It's a boring story, but it's real agent productivity. Another nice use case is quickly generating session transcripts for sharing. You can exclude the noisy intermediate messages, so the transcript shows the important parts of the session more cleanly. Try attaching a session transcript to your next PR so your teammate and their agent can review the provenance and prompting behind the change. If you're up for an additional challenge, ask your agent to "exhaustively review all agent history in this repo and find where the SDLC is struggling or isn't agent-native". Using past sessions to recursively improve the agentic SDLC is a loop that we're using a lot today. If you try it out, please let us know what you think! https://ift.tt/XrnplYJ July 2, 2026 at 09:28PM

Show HN: Searchable directory of 22k+ products from worker-owned co-ops https://ift.tt/61wyXHb

Show HN: Searchable directory of 22k+ products from worker-owned co-ops https://ift.tt/v2Aya0R July 2, 2026 at 02:17AM

Show HN: Z-Jail – A 130 KB Linux sandbox-C99 with 7 defense layers and zero deps https://ift.tt/QZ5n6wC

Show HN: Z-Jail – A 130 KB Linux sandbox-C99 with 7 defense layers and zero deps https://ift.tt/QulTK1E July 2, 2026 at 12:48AM

Show HN: QR code renderer in a TrueType font https://ift.tt/GhjbSnx

Show HN: QR code renderer in a TrueType font In the "Libre Barcode Project" discussion yesterday, 1bpp asked: "Is anyone willing to sacrifice their sanity for the sake of implementing a QR renderer as TTF hinting code?" Yes. I had some tokens to burn and was curious... turns out, it's possible. This was put together by a mix of Gemini, GPT, and Claude (depending on which usage limits kept running out). https://qr.jim.sh/ June 28, 2026 at 06:07AM

Show HN: Shot-scraper video tool for recording YAML-defined webapp feature demos https://ift.tt/5Si3Fsp

Show HN: Shot-scraper video tool for recording YAML-defined webapp feature demos https://ift.tt/kDyf7Ic June 30, 2026 at 10:28PM

Show HN: Fleet – a local-first console for managing Dockerized Hermes AI Agents https://ift.tt/oftlOpU

Show HN: Fleet – a local-first console for managing Dockerized Hermes AI Agents https://ift.tt/PEwmhkK June 30, 2026 at 02:01AM

Show HN: The UNESCO Tsunami Warning Emails Are Gone https://ift.tt/drnACw2

Show HN: The UNESCO Tsunami Warning Emails Are Gone This key piece of tsunami warning and safety was discontinued this morning and evidently there's no way to get it back. :/ https://ift.tt/UbNvXEd June 29, 2026 at 11:36PM

Show HN: Use-zerostack – delegate any task to a lightweight coding agent https://ift.tt/PluCqiK

Show HN: Use-zerostack – delegate any task to a lightweight coding agent https://ift.tt/BerTGPY June 29, 2026 at 01:03AM

Show HN: NanoEuler – GPT-2 scale model in pure C/CUDA from scratch https://ift.tt/HBuk6Yf

Show HN: NanoEuler – GPT-2 scale model in pure C/CUDA from scratch Hi everyone, I started working on nanoeuler after the ban of anthropic's fable because my ambition and dream is to work in the AI field in anthropic. The two interesting reasons that led me to create nanoeuler were (1) interfacing with llm does not mean understanding how they are composed and (2), working on llm with a very low-level layer to understand the correlation between parameters and data and growth of the model and how the GPU works and how some layers can be optimized. So I started working on it with a research aspect by making nanoeuler grow more and more but doing one step after another starting from Shakespeare.txt and understanding what a text generation model understands at 23 million parameters. For example, nanoeuler at that number had understood that Name: started a line and wrote that line with sense. I wrote everything in CUDA because I wanted to not use any intermediary between the model in training and inference and what it had to do. Then the use of SFT and much more, even if in small ways, were really useful to understand the various step to make an llm like a chatbot.Any feedback, help, or suggestions are absolutely welcome! https://ift.tt/aVdXS2O June 29, 2026 at 01:08AM

Show HN: Caliper – pass@k reliability testing for Claude Code and Codex skills https://ift.tt/qgayukA

Show HN: Caliper – pass@k reliability testing for Claude Code and Codex skills Skills for Claude Code and Codex are hard to test. What I mean by hard is that there's no standard way to do it. You evaluate the skill once on something, it looks like it works. You publish it. Then the new super model releases (GLM 5.2 anyone?), it will quietly break for some part, and you won't find out until your users complain. I also faced the same problem, so I tried to build something lightweight to stop doing that. Caliper. It's a local and lightweight harness that runs a skill k times in isolated environments and gives you a pass@k score (How much times it succeeded in these k times). As a non-deterministic technology, you can't just say "it worked once". You need to answer how much it passed in k times. You define success in a YAML spec. I picked YAML to keep a schema and make it still readable for a human. You either use a LLM judge, a Python assertion, or both: Here's an simple evaluation example with a JSON extraction, so you write this in a YAML file: tasks: - name: Extracts action items as clean JSON prompt: "Read /tmp/transcript.txt and write the action items to /tmp/actions.json." expect: "A valid JSON array where every item has owner, task, due. No markdown fences." assert: | import json items = json.load(open("/tmp/actions.json")) assert isinstance(items, list) assert all({"owner","task","due"} <= i.keys() for i in items) Then with the CLI, you'll run it: caliper run extract-actions.eval.yaml --k 5 --baseline What's cool about the --baseline flag is that it will re-runs everything without the skill, so you can see whether the skill is doing the work or the base agent was going to pass anyway: ID Task k(5) pass@k task-1 Extracts action items as JSON 5/5 100% PASS With skill 100% No skill 60% Delta +40% Most models know how to get the JSON right most of the time (JSON extraction was solved by 2 years old already). But that's it, "most of the time" is the bug. That delta shows how the skill actually helped. (It's sometimes 0%, sometimes -100%!) I also created two skills you can get started right away with your favorite harness, e.g. Claude Code, Codex or Pi: - evaluate-skill: run and manage evals without leaving your workflow - grill-skill: reads your SKILL.md, interviews you about what "good" looks like, writes a 3-task spec (happy path, edge case, adversarial), and runs it You can install the skill with the command: npx skills@latest add edonadei/caliper I for now support claude-code, codex, pi, claude-api, openai-api. You can run the agent and the judge as separate backends, so you can run a skill on one and judge with another. GitHub: https://github.com/edonadei/caliper PyPI: https://pypi.org/project/caliper-eval/ Of course, it's a first step. I think the autorater layer can be vastly improved, more handholding to create and iterate on evaluation specs, supporting more harness, why not including this layer into a self-improvement bigger system? If you're also building agentic evaluations, I'm genuinely interested to hear how you are handling that. https://github.com/edonadei/caliper June 28, 2026 at 11:12PM

Show HN: Starglyphs - A constellation puzzle game based on Euler paths https://ift.tt/9jCuPHo

Show HN: Starglyphs - A constellation puzzle game based on Euler paths I am a big Dragon Age fan and sunk hundreds of hours into Inquisition. It had this minigame called astrariums where you had to solve these shapes based on constellation guides by tracing stars. I'm a hobby game dev and wondered if I could procedurally generate these puzzles so they were always solvable. Turns out you can, so I built a space puzzle game around it with a colorful aesthetic. I released it in web form here but I'm currently working on getting it on Steam and mobile. https://starglyphs.com June 28, 2026 at 03:20AM

Show HN: Adrafinil – keep a lid-closed Mac awake only while agents work https://ift.tt/uYUrhoj

Show HN: Adrafinil – keep a lid-closed Mac awake only while agents work A month ago there was a wave of posts and tweets about engineers walking around cafes and parks with their MacBooks propped half-open, as fully closing the lid forces sleep that stops their AI agents. Some people made snarky comments about using tmux or Amphetamine, and some defended their choice with “but I only need it sometimes, and forgetting to disable Amphetamine and finding my laptop discharged in my bag is worse.” This is a solution to this problem. Unlike caffeinate, it will prevent your MacBook from sleeping even with the lid closed, with no external power or display, using pmset disablesleep 1. Unlike other sleep-preventing apps, Adrafinil only activates when there’s an agent actively doing something. It detects agent activity through hooks it installs into Claude Code, Codex, and others. To reassure you it’s working, the app shows the active status in the menu bar, and it plays a chime when you close the lid. Once the agent is done, Adrafinil detects it and lets the laptop go to sleep by setting pmset disablesleep back to 0. It will also let it sleep in case of overheating. And if you want to manually toggle it, you can install an optional MCP and tell your agent to keep the MacBook awake for a specific time. It has four binaries, one of which is a root helper exposing a single setSleepBlocked call. All the logic and policy live in the unprivileged parts. They’re all notarized, and the app is fully open source (MIT). https://ift.tt/6YeD5Em June 28, 2026 at 02:04AM

Show HN: Wind particles on Mapbox from a single EXIF JPEG https://ift.tt/xidvVYu

Show HN: Wind particles on Mapbox from a single EXIF JPEG https://ift.tt/tqXv0HP June 27, 2026 at 11:46PM

Show HN: A Living Neural Web in HTML5 Canvas https://ift.tt/gTivKnV

Show HN: A Living Neural Web in HTML5 Canvas https://techoreon.github.io/verpad/canvas-playground.html June 27, 2026 at 10:05PM

Show HN: TBD, a Mac-native CLI-forward coding agent multiplexer https://ift.tt/2I3TKB7

Show HN: TBD, a Mac-native CLI-forward coding agent multiplexer Inspired by Conductor, dmux, claude-squad, agent-deck, and Git Tower ## What makes it different: (Aside from GUI) A core tenet is -- everything a user can do manually, must be exposed via CLI for agents/automation Best paired with something that lets agents in different worktrees talk to each other (e.g. https://ift.tt/HTjYahr ) ## Background: I used and loved Conductor for months starting around January, but hit some persistent issues that made me realize that a core tool that I'm actively using for most of my waking hours sits too close to my skin to produce itches that I can't scratch myself After realizing I needed to switch to something hackable, I went through a few week-ish long trials of dmux, claude-squad, and agent-deck. They were all great, but I then realized I really didn't want to memorize keyboard shortcuts, and I've managed to put off learning how to drive tmux for over a decade, didn't want to end that streak XD So TBD happened in March. In the months since, it's gotten stable enough to the point where a few former and current colleagues have switched to using it as their daily drivers as well. It's been kind of like a fun little club house we contribute to The architecture is a daemon that handles the bulk of state management and actual work, and CLI and GUI clients as two interfaces. Users go through GUI, LLMs and scripts go through CLI. It works best for Claude Code (our shared daily drivers) but two of us also use Codex on the side, so there's some basic support there as well The only way to run it is to clone and build from source, partially b/c I imagine the main appeal is for people who need to hack on the thing they're using (but also b/c didn't want to shell out for an Apple dev license) I think it's now a good enough starting point for similarly minded folks to use as a base to fork and build your own variants, tailored to your own workflows https://ift.tt/Pmz4Fkp June 26, 2026 at 10:29PM

Show HN: Mantis, A self-hosted LLM gateway https://ift.tt/9uEkyB0

Show HN: Mantis, A self-hosted LLM gateway Hey HNers - Riz here. I got together with a few guys and we built an LLM gateway. It's designed for small teams working on early-stage products, and can be deployed to AWS using a single command (i.e. `mantis deploy`). It's self-hosted, and is designed to belong to you. https://ift.tt/tLYE9eq June 27, 2026 at 12:45AM

Show HN: Puzzle with Strangers. A free multiplayer jigsaw https://ift.tt/es4avwt

Show HN: Puzzle with Strangers. A free multiplayer jigsaw I built this over the last few days. Me and handful of friends are successfully hooked. I recently went to a — for lack of a better word – social/collaborative performance at an art gallery in Berlin where a group of artists filled a huge industrial hall with wooden 10x10cm cubes for people to build structures with. It was beautiful how universal the concept of playing with wooden blocks is and how ephemeral the structures were, people of all ages were put back into a childlike play. The thought about what kind of games need zero explanation stuck with me and i built an anonymous multiplayer jigsaw. We've already spent hours in there and you're invited now as well. Hope you enjoy. https://ift.tt/okCpys9 June 26, 2026 at 10:17PM

Show HN: I created a Scrabble-like word game with simple rules and fun combos https://ift.tt/GayFv3W

Show HN: I created a Scrabble-like word game with simple rules and fun combos When I was in school, my teacher used to play this game to our class. You add one letter turnwise and try to make a word. Later, I tried searching for this game but didn't find the exact match anywhere. The closest was Scrabble, but it was too complicated. So, I decided to build my own. I did make some modifications to make the game more challenging and fun. Back then, we would start with a blank board and also score 2 letter words. Here, the game gets prefilled with random letters so the game becomes more different each time. No scoring for two letter words. The best thing that I added was the combos. If your letter makes 2 or more words, you will get a multiplier for each subsequent word, so the challenge becomes finding a way to score more combos. Initially, I wanted to assign values to each letter like Scrabble, but after running multiple AI-to-AI experiments, I concluded that having flat values per letter increases variances in the game and also reduces the first turn advantage to 0. I still added the weighted game mode if you would like to give that a try as well. And I also added daily puzzles where you get 5 boards, and you need to find the best spot and best letter that scores the most. You can share the Wordle-like result to your friends. You can also play directly on the web at https://ift.tt/1RAp0La or free download in the App Store at https://ift.tt/gPnUha1 https://letterphile.com June 26, 2026 at 03:37AM

Show HN:Every Team Is Building the Same Cache https://ift.tt/zr2pVnw

Show HN:Every Team Is Building the Same Cache https://ift.tt/bOijAHJ June 26, 2026 at 03:10AM

Show HN: Full featured language that compiles to binary https://ift.tt/pKmvXM2

Show HN: Full featured language that compiles to binary Features: 1. Self-hosting compiler 2. C99 backend 3. Built-in dependency injection / IoC 4. Typed business-rule features like decision tables 5. Native binaries + WASM 6. Real app built with it: eXstream https://ift.tt/ERkhTPy June 26, 2026 at 12:45AM