Show HN: A second pair of eyes for electrical schematic review https://ift.tt/NBoDW0r

Show HN: A second pair of eyes for electrical schematic review https://bvcircuits.com/ July 31, 2026 at 10:16PM

Show HN: Tally – check a spreadsheet's numbers against their source, in-browser https://ift.tt/zjo9LCd

Show HN: Tally – check a spreadsheet's numbers against their source, in-browser https://ift.tt/6oPxIRZ July 31, 2026 at 12:55AM

Show HN: I made a game where you build a CPU from logic gates https://ift.tt/yCL26kh

Show HN: I made a game where you build a CPU from logic gates I built ChipBuilder to make computer architecture more approachable through interactive puzzles. You start with basic logic gates like AND, OR, and NOT, then gradually combine them into adders, multiplexers, memory, an ALU, and eventually a complete CPU. Once you've built the hardware, you can write assembly programs that run on the processor you created. The game is inspired by courses like Nand2Tetris, but everything runs directly in the browser with a visual circuit editor, simulations, and progressively harder challenges. https://ift.tt/SvW4Ycu July 30, 2026 at 06:33PM

Show HN: Rivora – An open-source memory layer for engineering tools https://ift.tt/S0DfdEG

Show HN: Rivora – An open-source memory layer for engineering tools https://ift.tt/3W2deTh July 29, 2026 at 11:04PM

Show HN: NoClick – Build always-on agents with your existing AI subscriptions https://ift.tt/5ugHQiN

Show HN: NoClick – Build always-on agents with your existing AI subscriptions Hey HN! Been working on a platform that lets you build always-on background AI agents that work with your existing subscriptions/harnesses of choice (Claude Code, Codex, OpenCode, Hermes, OpenClaw). Works in three steps: - Choose your agent harness (CC/Codex/OpenCode/Hermes/OpenClaw) and connect your corresponding subscription - Select the tools across 150+ integrations you want the agent to have access to - Decide when the agent should run (recurring schedule, app event, webhook, etc) All the infra behind the scenes (spinning up a sandbox to run the harness, connecting selected tools to it, persisting files across agent cold starts, observability for tool calls, etc) is automatically handled. Happy to answer any questions! https://ift.tt/Q9Nxskd July 28, 2026 at 11:48PM

Show HN: Open-source, Long-horizon cite-able memory for multi-agent systems https://ift.tt/3adKFUk

Show HN: Open-source, Long-horizon cite-able memory for multi-agent systems Two agents that share no model, no vendor, and no trust can cite the same signed fact and each verify it alone. Devices e.g. satellites, robots, CCTVs fill the memory today; any machine that watches the world joins by proving how it ran. https://ift.tt/ich7g5p July 28, 2026 at 10:47PM

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

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/45eYC9k 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/dMuwXT5 Site: letsseal.org Thx https://ift.tt/dMuwXT5 July 27, 2026 at 10:52PM

Show HN: FeyNoBg – Automatic background removal model and training library https://ift.tt/42yG8wW

Show HN: FeyNoBg – Automatic background removal model and training library Hey HN, I’m Shreyash from Feyn. We help companies build custom models from their data. Today, we’re releasing FeyNoBg, an automatic background removal model. Alongside it, we're open-sourcing NoBg, the Python library we built to train and run it. Try the model here: https://ift.tt/5sVGQPN . Check out the library here: https://ift.tt/pdbw2WT Some sample outputs: (1) Soccer Freekick: https://drive.google.com/file/d/1MZkAGLwbhNVOZ0Oi7XvpCfSEu9Q... (2) Hair in wind: https://drive.google.com/file/d/1Odc2m0XMVH9uZtvI_KjaRbXzhLL... (3) Bicycle with visible spokes: https://drive.google.com/file/d/1h99ahjfrtS1MFQJJgiKE2fuM3HZ... (4) Live Demo video: https://youtu.be/b1heHPvY8BM Background removal separates an image's subject from its surrounding. We've all tried it at some point. Often it is to reuse the subject in a different artifact. Nowadays, it is common to make chat stickers out of it. It is one of the most common but under-appreciated uses of AI. It is also surprisingly complex. Models can be easily confused by camouflage, motion blur, or fine structures like hair. The task requires two skills. First, a model has to identify the foreground. Second, it has to trace the foreground’s boundary and estimate an opacity value for each pixel. Generally, these skills are taught with different datasets. That creates a failure point. A poor training mix can improve one skill at the expense of the other. We saw this in our controlled evaluation. A training run with just the MaskFactory dataset improved on the CAMO benchmark but regressed on DIS5K. For FeyNoBg, we took an interpretability-first approach to training. We first studied how BiRefNet’s stages contribute to finding the foreground and reconstructing its boundary. We discovered that the third stage of it's feature extractor holds a lot of information. Both localization and boundary reconstruction depend heavily on the feature map produced here. This led us to expand this stage from 18 to 24 blocks while preserving the pre-trained weights. We then trained FeyNoBg on 26.1K diverse examples assembled from 10 datasets. The goal was to improve foreground identification and boundary precision without sacrificing either one. Across eight benchmarks, FeyNoBg achieves the best published score on four and comes within 2% of the leader on the rest. Building FeyNoBg also exposed a tooling problem. Image matting models are usually released as isolated repositories with incompatible preprocessing, training, and evaluation code. We built NoBg to solve this. NoBg puts these workflows behind one Python interface. It supports BiRefNet today, with more architectures coming. We hope you build something exciting with it! Happy to answer any questions! https://ift.tt/T3OSXuj July 27, 2026 at 11:59PM

Show HN: Infrawrench – a tool to manage cloud and svcs with workflows and chat https://ift.tt/DAVTva5

Show HN: Infrawrench – a tool to manage cloud and svcs with workflows and chat https://infrawrench.com July 27, 2026 at 11:25PM

Show HN: An interactive way to exploit an LLM without going to jail https://ift.tt/31B5Nkp

Show HN: An interactive way to exploit an LLM without going to jail https://ift.tt/9iSdLuX July 27, 2026 at 01:16AM

Show HN: Temporal Context Map https://ift.tt/ZAIQUtc

Show HN: Temporal Context Map Timeline with depth. https://ab.neudice.eu/ July 26, 2026 at 07:59PM

Show HN: IPAbet – A fast, memorable keyboard for International Phonetic Alphabet https://ift.tt/no5TDUc

Show HN: IPAbet – A fast, memorable keyboard for International Phonetic Alphabet https://ipabet.org July 25, 2026 at 09:41PM

Show HN: Crisp – Open-source display manager for macOS (DDC, HiDPI, presets) https://ift.tt/aC8t3RM

Show HN: Crisp – Open-source display manager for macOS (DDC, HiDPI, presets) I recently bought a new 1440p monitor and connected it to my mac, but at native resolution the UI felt so tiny and unfamiliar. I'm fairly new to mac in general so I checked my options for scaling, but quickly learnt (afaik) that this wasn't a thing for external monitors. I found some options in BetterDisplay and Lunar, but it felt stupid to pay for a feature that should be included. FreeDisplay seemed like the perfect option, but when I tried it on my mac it didn't work for me. Development seemed stale so rather than adding a PR, I forked it and fixed it. After that I wanted to do some changes and add some features, which suddenly ended up in a full rewrite. It covers the thing I initially wanted, which was HiDPI, but I also wanted it to look native, so I added some native elements. I kept the display arranger and fixed a lot of the issues with e.g. auto and combined brightness, profiles for the monitors, presets etc. Can be installed with brew (brew install --cask didriksg/tap/crisp) or use the dmg file in the releases in the repo. It’s unsigned though, so you’ll probably get some warnings I’ve been using it for a week now and thought I’d share it with anyone that wants it. Open source and PRs are welcome. https://ift.tt/mtPp65r July 24, 2026 at 11:05PM

Show HN: Flow Matching model inference in C https://ift.tt/rGhqEPn

Show HN: Flow Matching model inference in C As the title and description of the GitHub repo suggest, I’m working on a small project for purely educational purposes, with the goal of implementing generative model inference (small models capable of modeling 2D distributions) based on the Flow Matching paradigm in C. I’ve worked on generative AI models based on Flow Matching from a more “abstract” perspective, using frameworks like PyTorch, and I wanted to understand what goes on behind the scenes. The repository is still a work in progress and is also one of my first "serious" projects in C. https://ift.tt/VZ6OXHd July 24, 2026 at 12:01AM

Show HN: NeoBox – a native macOS NeoGeo emulator front end https://ift.tt/GsfHySq

Show HN: NeoBox – a native macOS NeoGeo emulator front end I am 90's kid. And NeGeo console was something I always longed for and only ever saw ONE person ever owning! For those who are following...there's a new NeGeo AES console coming out later in the year! I got excited and wanted to remember playing OG SNK games that I loved (Super Sidekicks, Metal Slug, Art of Fighting). I first reached for the amazing OpenEmu native macOS emulator fronted, but found out it did NOT have support for NeoGeo console (FYI I later found out there is experimental support for it) MAME is there, but wanted a nicer macOS fronted similar to Openemu. I've built plenty of macOS / iOS in my career before (for fun and professionally). So decided to give it a shot. Soon this turned into NOT just a MAME frontend...but I wanted a NICER experience and embedded the amazing libGeoLith emulator library. NeoBox can use either GeloLith (iwht native Metal rendering pipeline) or a frontend for a self-managed MAME installation. So... what was AI generated and what wasn't: * Main native macOS frontend was all hand written code, nothing fancy here. Just native AppKit code * Painstakingly testing as many NeoGeo ROMS as possible and fixing bugs AI-assisted: * Website (duh ;) ) * libgeolith and Metal rendering pipeline. This truly was new terrority for me and I could NOT have done this without AI. I'm not well versed in graphics rendering pipelines so it was amazing to me how well Claude was in getting this working! My goal...simple...hoping it funds my purchase of the new NeoGeo AES+ Ultimate Edition console :) That's it! Mac App Store Link: https://ift.tt/m6V5cvn... https://neo-box.app July 23, 2026 at 10:42PM

Show HN: Brew doctor` for Skills and MCP loadouts https://ift.tt/y8Ec5Tm

Show HN: Brew doctor` for Skills and MCP loadouts Recently, I've had agents reach for the wrong skill or tool. This tends to happen in the middle of longer reasoning chains, which frustratingly means lots of chatter polluting the context before a correction can be issued. To chase these issues down, I built `drskill`: a CLI tool that checks for conflicts and security issues among your agent's Skill and MCP loadout. In addition to spotting conflicts that might trip up your agents, security alerts were added as well. Did an MCP provider silently add a tool due to a supply chain attack? Running `drskill` on bootup or during CI will flag those changes. `drskill` works without access to an LLM, though connecting it to one will yield better conflict reports and allows for suggesting alternate, non-clashing descriptors. A ledger is maintained globally and locally, tracking acknowledgements and preferences. This is the type of tool that heavily benefits from contributions (your loadout is very different than mine!), so please file issues or submit PRs if you're interested. https://ift.tt/TpNWFjA July 22, 2026 at 10:50PM

Show HN: PMG, open source package firewall https://ift.tt/x0E7eDC

Show HN: PMG, open source package firewall Hi HN I am the founder of SafeDep. We have been detecting malicious packages for a while. Coming from DevSecOps background, I always considered malicious package detection & protection to be a build stage problem. But I was wrong since the S1ngularity and early Shai-Hulud days. In 2026, we pretty much started worrying more about our own dev machines than CI/CD environment. Depending only on threat intelligence data (OSV / SafeDep / Socket / any other source) to protect our own dev machines did not feel right. We wanted to build a multi-layered protection that can get 100% visibility of OSS packages coming in, and can protect against known and “hopefully” unknown threats. That’s how Package Manager Guard (PMG) started. Core idea was simple: - Start a local proxy (localhost) - Make sure supported package managers like npm, pnpm, pip etc. goes through it - Use threat intelligence data to fail fast on known malicious packages - Apply policies like dependency cooldown as additional guardrails - Adopt a policy language like CEL to support custom policies (roadmap) - Everything stays local with stackable policies and audit log - Threat model - Protect “willing” developers against malicious open source packages Note: PMG does not consider a malicious developer as part of its threat model. So no real effort has been put to “enforce”, rather the goal is reduced friction while being effective. Then came across Anthropic’s SRT and suddenly realized that in-process OS-native sandboxing is a good solution for limiting blast radius against unknown threats, especially since package managers have predictable runtime behaviour that can be allowed via. a sandbox while denying larger user permissions. Adopted seatbealt on MacOS and Landlock + Seccomp BPF for Linux. Seccomp BPF with Go was a battle of its own due to lack of control on OS threads, but finally managed to get it working without major performance cost. To summarize, PMG does not only depend’s on SafeDep’s ability to find malicious packages. It enforces dependency cooldown (useful if you are stuck with older npm/pnpm), sandbox to protect against malicious packages. Our near term goal is to support CEL as a policy language and improve tooling around sandbox rules to make adoption easier. Any feedback is welcome. https://ift.tt/96mhksw July 21, 2026 at 11:58PM

Show HN: Cross-Harness self hosted registry and analytics for AI Agents https://ift.tt/BfU5qus

Show HN: Cross-Harness self hosted registry and analytics for AI Agents https://ift.tt/6AuUPji July 21, 2026 at 11:57PM

Show HN: LectureToBook – Turn Videos into a PDF/ePub https://ift.tt/EdlDuLz

Show HN: LectureToBook – Turn Videos into a PDF/ePub Lecturetobook takes a video presentation and turns it into an editable document, with photos, diagrams, etc. extracted from your slides. I came up with this idea because I was enrolled in an online course and it was all videos. I spend all day long on the computer for work, so the last thing I want to do after work is spend more time staring at a screen. I wanted something that could take those videos and turn them into a readable format. The most difficult part was detecting what frames in the video are slides, and extracting from those what is useful content to add to the document. I didn't want to just stick a screengrab of the slides in the text, I wanted it to read like an actual book, so it uses an AI model to take from the slides what is useful and ignores what is just repeated in the transcript. Here is an output sample from an NIH video: https://ift.tt/ePIyLsp Feedback welcome! This is my first side-project that has made it to launch. https://ift.tt/kLps0dM July 20, 2026 at 10:36PM

Show HN: Bribes.fyi – Built something to report bribes https://ift.tt/m3Dfqvc

Show HN: Bribes.fyi – Built something to report bribes https://bribes.fyi/ July 19, 2026 at 10:31PM

Show HN: PostgreSQL course with database running in your browser https://ift.tt/SnWBAEe

Show HN: PostgreSQL course with database running in your browser I wanted to brush up my SQL skills and was looking for an online course that included a live DB. Most PostgreSQL courses require you to create an account or pay. This is probably because they have to bear the costs of running a full server-side database. So I created learnpg.xyz, a collection of PostgreSQL SQL exercises that run client side. Sharing here because it might be of use to people! https://learnpg.xyz July 19, 2026 at 08:58PM

Show HN: Peek-CLI: Let Claude Code iterate on front end designs https://ift.tt/snk1gt7

Show HN: Peek-CLI: Let Claude Code iterate on front end designs https://ift.tt/xdANB0X July 19, 2026 at 02:02AM

Show HN: SDF Pelicans on Bicycle https://ift.tt/VQpl45f

Show HN: SDF Pelicans on Bicycle https://ift.tt/u9Z7UQT July 19, 2026 at 02:17AM

Show HN: Get alerts for good seats at 70mm IMAX showings of The Odyssey https://ift.tt/ei6bNBj

Show HN: Get alerts for good seats at 70mm IMAX showings of The Odyssey https://imaxxing.io/ July 19, 2026 at 01:06AM

Show HN: Randomly Generated ASCII Trees https://ift.tt/eNwshuZ

Show HN: Randomly Generated ASCII Trees Code : https://gist.github.com/Soham-Saha/12296c059cea074b2fed5e97a... https://ift.tt/hlPi9KQ July 18, 2026 at 10:57PM

Show HN: Lific: Issue trackers should be simple, right? https://ift.tt/2wpNzWv

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 18, 2026 at 12:52AM

Show HN: A zoomable timeline of 4M Wikipedia events https://ift.tt/owHUOyc

Show HN: A zoomable timeline of 4M Wikipedia events I'm building a journal app in Kotlin Multiplatform and for this purpose I have created a zoomable timeline interface. This is a side-project where I reuse the timeline interface to display 4 million events imported from Wikipedia / Wikidata, scored using PageRank. There is more information on the about page. If you're interested in the stack: I use Kotlin Multiplatform extensively, with Compose Multiplatform for the UI, communicates with the backend using Kotlinx-RPC and behind the hood a simple Postgres database on a Hetzner machine. https://ift.tt/XFnBLZ2 July 18, 2026 at 01:37AM

Show HN: Proton – A Pure Go, Immediate-Mode GUI Library (Zero CGO) https://ift.tt/JV0cit8

Show HN: Proton – A Pure Go, Immediate-Mode GUI Library (Zero CGO) Hi everyone, I’ve been building Proton to solve a specific pain point in the Go ecosystem: building native GUIs without the "web dev" trade-offs or CGO complexity. If you’ve tried to build desktop apps in Go, you’ve likely dealt with the frustration of CGO dependencies, bloated build pipelines, or feeling like you’re just writing a thin wrapper around a browser. Proton aims to fix this with a clean, pure-Go approach: Zero CGO: Cross-compile to Windows and macOS seamlessly from any machine. Immediate-Mode API: No setState, no complex component trees, and no XML. You just write your draw function, and it runs every frame. API Immunity: The public API is shielded from the underlying rendering engine (built on top of Gio). If the backend changes, your code remains untouched. Full Feature Set: Includes inputs, lists, overlays, alerts, and 46 built-in themes (or easy custom hex-code styling). It’s currently in development for v0.4.0, but it’s stable enough for cross-platform apps and even supports Android deployment out of the box. I’d love to hear what you think, especially if you’ve been looking for a more "Go-native" way to handle GUIs. Repo: https://ift.tt/miVGnjr July 17, 2026 at 10:20PM

Show HN: QBasic Gorillas (Repeeled) https://ift.tt/Nj7F5ca

Show HN: QBasic Gorillas (Repeeled) I've found the most engaging way to practice techniques for AI-assisted development and test models is to build fun side projects in vanilla JS. I spent many hours playing (and studying and editing) QBasic Gorillas, and this is a vanilla JS implementation using Fable and Opus. Play 1-on-1 hotseat or against the computer. A bit of extra camera snazz as well. https://ift.tt/XNgrpGE July 16, 2026 at 09:34PM

Show HN: Lineation – One security control plane for all agents https://ift.tt/h6M9frk

Show HN: Lineation – One security control plane for all agents TLDR: Distributed policy enforcement and a "black box" for AI agents https://lineation.ai July 15, 2026 at 11:25PM

Show HN: A device for never missing the surf turned into something more https://ift.tt/Zq6Lu7G

Show HN: A device for never missing the surf turned into something more https://ift.tt/W1x0QAu July 15, 2026 at 02:12AM

show hn: 1d data to 3D topology, AI deepfakes to protien folding https://ift.tt/EBSvUer

show hn: 1d data to 3D topology, AI deepfakes to protien folding https://ift.tt/8Xr9PpH July 15, 2026 at 12:29AM

Show HN: Pullrun – Run One OCI Image as a Container, Firecracker, or Apple VM https://ift.tt/x6ey8QC

Show HN: Pullrun – Run One OCI Image as a Container, Firecracker, or Apple VM https://ift.tt/C6fq487 July 15, 2026 at 12:19AM

Show HN: BeePub – A reading-first alternative to Calibre-Web https://ift.tt/yxHYgkO

Show HN: BeePub – A reading-first alternative to Calibre-Web I've used Calibre's content server and calibre-web, and for actual reading I was on Calibre + Apple Books. It got the job done, but it never felt smooth — so I built my own, working with Claude Code. It's fully compatible with Calibre — that's how I run it myself: my books still live in a Calibre library, and BeePub just points at it and stays in sync (read-only; Calibre remains the source of truth). Same as calibre-web. I've put a lot of work into CJK / Traditional Chinese support (including vertical text), and into manga EPUBs. There's also a native app built with Capacitor, currently on TestFlight (iOS). It also speaks OPDS and KOReader progress sync (kosync), so it plays nicely with e-ink readers. If you're curious, play with it at https://demo.beepub.app (login: demo / demodemo — the data resets every 6 hours). This is a project I dogfood every single day, so expect it to keep getting updates! https://ift.tt/Aib1jQL July 14, 2026 at 11:21PM

Show HN: Jacquard, a programming language for AI-written, human-reviewed code https://ift.tt/g29xiGE

Show HN: Jacquard, a programming language for AI-written, human-reviewed code https://ift.tt/1eDzEGR July 13, 2026 at 10:56PM

Show HN: Vigil – open-source TimeTracker with steroids https://ift.tt/PXLEw1Q

Show HN: Vigil – open-source TimeTracker with steroids https://ift.tt/Fw5XqZQ July 12, 2026 at 10:45PM

Show HN: Quantum hardware now fault-tolerant without extra engineering https://ift.tt/sB3YgwK

Show HN: Quantum hardware now fault-tolerant without extra engineering Before you say it's impossible, please go try. --- CIQA, an analytic Quantum Error Correction code, is now freely accessible on GitHub alongside CIQS, the 'million-qubit compiler'. Here's a brief overview of the stack: 1. CIQS - An analytic circuit transpilation pipeline (no heuristics, no tunable parameters). It passed the full IBM Benchpress transpilation suite (892/892 tests) in 75 minutes on older hardware, while Qiskit took 17+ hours. It scales linearly to 1M+ qubits on the same harness (that is one million and above). 2. CIQA - An analytic 1:5 QEC that enables full active computation and complete Pauli correction at depth on existing hardware. On real quantum hardware, it delivered a mean fidelity improvement of up to +0.832 over bare qubits. On the same hardware, it successfully ran the full Hayden-Preskill black hole circuit, preventing early decoherence, and enabling the first observation of black hole evaporation past the Page time. CIQS and CIQA were validated on IBM Heron r2 during real, deep computation runs. Both natively handle quDits, and both are hardware-agnostic. --- CIQA is added to the CIQS GitHub repository as part of the full pipeline. CIQA can integrate any stack, but when paired with the CIQS compiler, the pipeline automatically isolates the CIQA encoding prefix (no extra coding needed). All benchmarks are documented and public, alongside published papers. All links are in the GitHub README. --- ## Note on CIQA's overhead 5 physical qubits from the [[5,1,3]] perfect quantum code layout + 2 dedicated ancilla qudits per logical block (one per channel) for syndrome extraction. For a 156-physical-qubit QPU: 156/7 ≈ 22. For 156 physical qubits, CIQA delivers 22 fully protected logical qubits allowing deep computation on real QPU, today. --- What experiment will you attempt first with it? Feedback is welcome. https://ift.tt/6rZTHad July 12, 2026 at 12:33AM

Show HN: Earth Game – An offline CLI for turning life goals into quests https://ift.tt/fm9D841

Show HN: Earth Game – An offline CLI for turning life goals into quests https://ift.tt/9dEHv8N July 11, 2026 at 11:37PM

Show HN: Reviving my 2001 college band with AI https://ift.tt/3tb4Pwg

Show HN: Reviving my 2001 college band with AI 25 years ago, I joined a band called Fading Maize at Ripon College in Wisconsin. We did what we could with what we had. We recorded 3 albums over the next 3 years and played at as many bars and coffee shops as we could. We built a website with Microsoft Frontpage. Then we went our separate ways, got married, had kids, focused on other things. Earlier this year I had the idea to approach the lead singer who wrote all of the lyrics and melodies to the stuff we played back then, and wanted to "reimagine" everything in 2026 using AI. That's the project I want to share here! The site has a before/after player where you can flip between the original dorm-room recording and the 2026 version mid-song without losing your place, so you can hear exactly what changed. The original 2001 website is preserved and browsable at https://ift.tt/Hy5IrNc , rough edges intact. Working on this, the thing that sparked in my own mind is that it was an experiment in a certain way to use AI. The songs, lyrics, and arrangements are the original human work (in this case from 2001-2003). We wrote the lyrics, we created the melodies, we played the parts, it just didn't sound as good as we heard it in our own heads. The stuff AI creates is awesome, but it means less if it's just the AI cranking everything out from the ground up. In our case, the AI was only there to help us get the results we originally wanted back in 2001 when we were cooking ramen in our dorm rooms and couldn't afford anything fancy Being fully transparent about our use of AI, sticking tightly to our original lyrics and melodies, but making full use of AI to give us the studio, session players, and production budget we never had seemed like the right balance of concerns. I'm super proud of how it turned out and the transparency we've used along the way. Happy to discuss the audio pipeline, the site (Next.js), or what it's like to A/B your 20-year-old self! p.s. Oh and check this out! I remember this day. Our site was getting absolutely hammered! https://www.youtube.com/watch?v=KPJWlnN9tSE&t=43 https://ift.tt/NJqhe4f July 10, 2026 at 02:49AM

Show HN: PastPage – Find archived versions of dead links https://ift.tt/nHIC1VE

Show HN: PastPage – Find archived versions of dead links hi, i'm a journalist and i made PastPage because i often need to check for archived versions of urls. this browser extension helps me a lot. it autmates the process of checking lots of different web archives. also, it helps with 404 etc. i made it free and open source, and it have great privacy practices, e.g. i don't see which url you are searching. i'd like feedback and i don't want to make money. https://ift.tt/Q2B6GPF July 10, 2026 at 09:43PM

Show HN: GodUI – Open-source React components with a shared motion system https://ift.tt/pxqiGwQ

Show HN: GodUI – Open-source React components with a shared motion system https://godui.design July 9, 2026 at 11:23PM

Show HN: Reverse-engineering web apps into agent tools https://ift.tt/rMsiupm

Show HN: Reverse-engineering web apps into agent tools Hey HN! We built a browser-based agent that runs inside an authenticated web app, watches how the app calls its own APIs, and automatically turns those into agent tools. You can think of it as an auto-generated MCP server that self-updates as the host app changes. The result is a skilled AI assistant that actually integrates deeply with any product (not just chat and RAG) with minimal effort. Check out these short demos below that show the agent in software you're probably familiar with: - Jira: https://ift.tt/TyCdF7I - Spotify: https://ift.tt/XQ8gkE0 - Hacker News (lol): https://ift.tt/AvFxMlN - Full Demo: https://ift.tt/ZFOCe41 As you can see in the examples, you can do way more (and faster) than what you normally would be able to via point and click. And we never even touched the source code of these products! Why do this? In an ideal world, every application has an MCP server or an easily-digestible API available for AI agents to feed from. In practice, we found that even very modern software tends to have a spider web of confusing APIs and services that AI agents simply cannot use out of the box. Security also becomes a huge issue as applications have different (often homebrewed) standards for how endpoints are secured (JWTs/cookies/mix of both). Finally, having an actual browser agent go in and use the application on behalf of the user (i.e. computer-use), is simply too brittle, slow, and burns a lot of tokens. We took our existing browser agent that’s already trained to use and learn authenticated applications, and added an extra step that automatically turns the app’s authenticated APIs into "recipes". A recipe is a mix of the following: - API endpoint + method - Authentication method (and how to retrieve refresh auth tokens/cookies) - Response schema - Input schema (for POST/PUT) - Human readable description of what the tool does Putting it all together, these become reusable tools for LLMs, all without writing or maintaining any code. Even if the APIs change our agent figures this out and replaces the recipe for the tool with the updated version. Adding tools to an AI agent becomes super simple this way: - Our agent trains on the app and builds the recipes - The app owner enables discovered tools from our dashboard - The agent can now take actions on the user’s behalf directly inside the application. For instance, saying something like "invite my teammate to my workspace" would securely call the existing API endpoint for inviting users without proxying or relaying through a third party. Of course, there's a ton of edge cases you run into when you try to do this - every application is intrinsically different despite how many "standards" exist. Fun fact: graphql was by far the worst API to work with in standardizing the recipes. Looking forward to your feedback/comments! July 9, 2026 at 10:45PM

Show HN: Hover over your UI element to get its exact location in code https://ift.tt/Ued5KNM

Show HN: Hover over your UI element to get its exact location in code https://loerei.github.io/HoverSource/ July 9, 2026 at 12:44AM

Show HN: Maps for e-scooters (hills and battery routing) https://ift.tt/IxWrhQB

Show HN: Maps for e-scooters (hills and battery routing) I built BattMap, AMA! Living in San Francisco is hilly. Google Maps is great for bike maps, but I wanted to know if my scooter could make it up the hills, how much battery it would burn, and if I could make it back home without recharging it. https://battmap.com July 8, 2026 at 11:06PM

Show HN: Signal for LLM – The Modulator Architecture (Theory Complete) https://ift.tt/yG0Vmhl

Show HN: Signal for LLM – The Modulator Architecture (Theory Complete) https://divinecanon.github.io/signalengine-EN/ July 7, 2026 at 11:11PM

Show HN: A website that shows every pro triathlete's swim, bike, and run gear https://ift.tt/U60MCjc

Show HN: A website that shows every pro triathlete's swim, bike, and run gear https://racekit.pro July 6, 2026 at 11:18PM

Show HN: Pulpie – Models for Cleaning the Web https://ift.tt/iJD0c4V

Show HN: Pulpie – Models for Cleaning the Web Hey HN, I'm Shreyash, founder of Feyn. We built Pulpie, a family of Pareto optimal models for cleaning the web. Pulpie strips boilerplate (ads, footers, sidebars) from raw HTML and returns just the main content as HTML or Markdown. We match SOTA extraction quality while being 20x cheaper. Cleaning 1 billion webpages costs $7,900 with Pulpie versus $159,000 with Dripper, the current leading extractor. The gains come from architecture. Today's leading extractors are decoders that generate output one token at a time. Each step reads the full model from memory to produce a single token. Conversely, Pulpie models are encoders. They run one forward pass over the full input HTML and label each block as boilerplate or content. As a result, Pulpie is compute-bound while decoders are memory-bound. Cheaper GPUs have relatively more compute than memory bandwidth. This makes Pulpie easy to run optimally. Here's Pulpie and Dripper cleaning the same pages side by side: https://www.youtube.com/watch?v=ibd-tIiQECo . You can try a side-by-side comparison yourself: https://ift.tt/yzcDG2w Our motivation for Pulpie came from building a deep research harness. Every search API returns noisy content that contains ads, nav elements, and sidebars. In one instance, an ad for "Gemini on Pixel" slipped into our search results, got passed into LLM context, and ended up in the final answer served to the user. Pretty embarrassing moment for us but it helped us realize how bad data kills model intelligence. We built Pulpie to get clean data for cheap. All models are open source on Hugging Face. You can read about our training process and how to use Pulpie here: https://ift.tt/oD3VSZa... Happy to answer any questions! https://ift.tt/ZJST2Rq July 6, 2026 at 11:04PM

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

Show HN: Handoff – a verified context bridge between Claude Code sessions https://ift.tt/gvjKn3A July 6, 2026 at 12:18AM

Show HN: EdgeRunner – run GGUF models with Swift and Metal https://ift.tt/hV5tuaw

Show HN: EdgeRunner – run GGUF models with Swift and Metal https://ift.tt/uw8NM6v July 6, 2026 at 12:21AM

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

Show HN: Gemma 3 inference in pure C++ with Metal acceleration https://ift.tt/moh9BIz July 4, 2026 at 10:54PM

Show HN: Groot – Kubernetes incident evidence in one .tar.gz https://ift.tt/ln9rjNb

Show HN: Groot – Kubernetes incident evidence in one .tar.gz https://ift.tt/4OyaLKE July 4, 2026 at 07:31PM

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

Show HN: Dockside – I turned unused space around the macOS Dock into a workspace https://ift.tt/YUzr7Ou July 4, 2026 at 01:05AM

Show HN: Mcpsnoop – Wireshark for MCP (transparent proxy and live TUI) https://ift.tt/Yz7Ddt5

Show HN: Mcpsnoop – Wireshark for MCP (transparent proxy and live TUI) https://ift.tt/VIqWCAd July 3, 2026 at 11:53PM

Show HN: Ultracodex – Run Claude Ultracode Dynamic Workflows with Codex Agents https://ift.tt/v1NKdIB

Show HN: Ultracodex – Run Claude Ultracode Dynamic Workflows with Codex Agents Claude Fable has been incredible, however the plan usage runs out too fast, especially if you use ultracode mode (Claude Code's workflow feature, where the model writes small JavaScript programs that orchestrate subagents) and let the agents go brrr. I want Fable to focus on high-value tasks such as planning or verification, and not burn tokens on mundane implementation work. So I built ultracodex, an engine that spawns codex agents to complete the same ultracode workflows and hand off seamlessly to and from Claude. It runs the same workflow scripts that Claude writes. I designed this tool for anyone owning both Claude and Codex subscriptions or anyone who enjoys Fable and wants to make the quota last. This tool is in early days but I am very excited about the potential. I think it’s also a great “loop engineering” starter pack for us because 1) Claude is great at writing loops and 2) ultracodex runs the loops with Codex agents - given their generous limits, you don’t have to worry about usage much. So “loop engineering” is no longer a mysterious thing but a tool you can throw at any task. I have some examples of “loops” in my repo as well. Project is completely open-source. Apache-2.0, npm i -g ultracodex, demo video in the README. Please check it out! https://ift.tt/9xTyXUa July 3, 2026 at 10:45PM

Show HN: Bais.News – News Neutralization Piepline https://ift.tt/3swrRvj

Show HN: Bais.News – News Neutralization Piepline Solo dev here, been working on this project the last 7 months and I need some feedback. Bais aggregates news stories from a broad range of sources and synthesizes an article focused on reporting the overlapping coverage of all sources. The goal being to provide a fact first account while eliminating narrative spin and emotionally charged language. Happy for any feedback, thanks. https://bais.news July 3, 2026 at 12:29AM

Show HN: QUALITY.md – open format/specification, agent skill, and CLI https://ift.tt/kM8wfnE

Show HN: QUALITY.md – open format/specification, agent skill, and CLI Hello all, I created QUALITY.md to help build a holistic quality evaluation process for my projects. Turns out it's also ideal for loop engineering. I'm hoping this provides a valuable contribution to the conversation around quality and craft and having AI help us in the effort. I hope to shift the mindset from a reactive/review/repair mindset to a proactive care mindset. Give it a go. I look forward to your thoughts/comments/feedback! Website: https://getquality.md GitHub: https://ift.tt/IZQnupq https://getquality.md July 2, 2026 at 11:36PM

Show HN: I built an MCP to allow Claude to pair-program with another Claude https://ift.tt/AnaYXQ7

Show HN: I built an MCP to allow Claude to pair-program with another Claude https://ift.tt/uiOVWcR July 2, 2026 at 11:32PM

Show HN: AnalystAIPack – 118 runnable agent skills for malware analysis and RE https://ift.tt/yLkfH3b

Show HN: AnalystAIPack – 118 runnable agent skills for malware analysis and RE https://ift.tt/aBT2VRZ July 2, 2026 at 12:27AM

Show HN: Classify mechanical faults using Contrastive Language-Audio Pretraining https://ift.tt/D76p3c4

Show HN: Classify mechanical faults using Contrastive Language-Audio Pretraining https://ift.tt/5wYBUks July 1, 2026 at 11:57PM

Show HN: PMB – local memory for coding agents that shows if it is used https://ift.tt/4B2IPmg

Show HN: PMB – local memory for coding agents that shows if it is used https://pmbai.dev June 29, 2026 at 10:37PM