Show HN: GAI – A Go runtime for typed, tool-using LLM agents https://ift.tt/ENyfhQj

Show HN: GAI – A Go runtime for typed, tool-using LLM agents https://ift.tt/dyWb4Gx August 1, 2026 at 02:53AM

Show HN: Offline Flock Navigation https://ift.tt/iAke3Tr

Show HN: Offline Flock Navigation Hello HN! A little side project I have been working on a fork of OsmAnd with offline ALPR/Flock camera avoidance routing. Also, took the time to at least create a paper on the project as well. https://ift.tt/eRPNa57... And yes, I did use AI to help me with this. All of it open sourced and available for use. Though I don't intend to build Apple version of this, or submit it to the play store. I am looking for feedback! Thank you all and have great weekend. :) https://ift.tt/xJ3mBn0 August 1, 2026 at 12:10AM

Show HN: How to build and self-host a code review agent https://ift.tt/MShdcFg

Show HN: How to build and self-host a code review agent Hey HN, I've had a side-project that I've slowly ticked away at over the last year called Tilde. Tilde is a harness SDK platform - I've tried to take the best things of OpenClaw, Hermes & other harnesses and decompose them and make them available as cloud API building blocks. You can use Tilde to create AI agents for your use case, fast and self-host the agent's yourself. The documentation (and attached blog post) leave a lot to be desired in terms of technical documentation but hopefully the attached git repo does a good job of showcasing the API. https://ift.tt/lzL8JEH https://ift.tt/iaZhJmN August 1, 2026 at 12:27AM

Show HN: Local text, image, video, music and 3D from one CLI, no Python https://ift.tt/4Kw3ag6

Show HN: Local text, image, video, music and 3D from one CLI, no Python Hi HN! I'm the author of mere.run a local first inference runtime built around an installable CLI. I believe that whenever possible we should use the stuff we already own (like our Mac laptops, decent machines gathering dust, our gaming PC) and the limited electrical power we have easy access to, like the socket in the wall next to most of us. We shouldn't have to send our data to the cloud hoping some T&C will prevent it from being used in a way that we'd regret. Most of the local AI solutions are technical, involved, and land a curious body in some package hell. People are optimizing for one system and not another, the fun stuff is on PC if you own a Mac, and on Mac if you own a PC. So mere.run was my choice to begin to patch many of those things that I saw as problematic. Text, chat, code, image gen, speech tts+asr, vision (caption/ground/segment/track/pose/depth/face/OCR/etc), music, sfx, video, 2d->3d, persistent worlds, lora training plus a few more things I am probably forgetting all in one place to work the way you work, with a scriptable CLI, an openAI compatible serve, and optionally a native app on Mac. It's native swift on MLX, no python, PyTorch, diffusers for inference. For text lanes with GGUF it uses llama.cpp and for a/v muxing its FFmpeg. Most upstream releases that don't have an MLX variant are converted offline and hosted on huggingface. All release packages are built for arm64 (Mac & Cuda) plus x86. They're signed and ship SHA256SUMS. No windows at the moment. > mere.run model capabilities --recommended # That inspects your machine before recommending to prevent pulling models that don't fit your spec There's a workflow layer with typed, validated graphs so you can create immutable job bundles and run them locally, over an ssh executor or using a fleet of machines and the relay service. (It's hosted at relay.mere.run and is currently invite only while I test, but its also totally open MIT so you can set it up yourself) The whole runtime is MIT along with the companion packages, models carry their own licenses and the CLI makes it clear when something has specific terms. Once you've pulled the models, everything works fully offline. I've been working on a (hopefully) comprehensive docs -> https://docs.mere.run No account, no API key, no analytics or phone home. Any network calls in the source are all at your request only like huggingface.co (models), GitHub.com (Pi install). I'm just getting started, but it's finally at the point I'd love feedback, contributions, and just folks to generally find it useful. I hope it helps you make things and explore what's possible with the stuff you've already got in your home. Would love any thoughts, questions, ideas and maybe a star if you do that kinda thing. -Kyle https://ift.tt/Pg90sjX July 30, 2026 at 05:25PM

Show HN: Collie – a local AI harness that runs the browser, desktop and code https://ift.tt/SNHk4wZ

Show HN: Collie – a local AI harness that runs the browser, desktop and code https://ift.tt/D7cvI8T July 31, 2026 at 12:24AM

Show HN: Supapool – a Supabase per coding agent in ~400 ms https://ift.tt/oydFhYL

Show HN: Supapool – a Supabase per coding agent in ~400 ms hi HN, I built supapool.io, an ephemeral full copy of supabase's services that you can spin up in ~400 ms (Auth, postgres, storage, realtime). so if you run multiple coding agents in parallel in different worktrees, they can now have their own copy of supabase without making changes that conflict with eachother. > why not use supabase docker locally? when I run 3-4 instances locally, my macbook gets hot and sometimes freezes. > why not use supabase branches? branches take minutes to setup, and are designed for persistence. this is expensive, and for a dev environment, it is too slow. > why not use mocks? mocks are bad for agents. i expect agents to test their migrations, SQL against real prod service behavior. agents hallucinate working mocks often. However, upside of mocks is that its faster and runs locally, but with supapool, the upside is less convincing. > how does it work/how is this economically viable? starting supabase in 400ms requires a few things: 1. a pool of ready supabase instances running warm, and colocated with region failover (us-east, us-west, europe-west, asia-southeast) 2. fast autoscaling when pool starts to shrink with microVM/firecracker 3. gutting strong persistence guarantees. dev agents don't need WAL, fsync, PITR, replication. anything for HA on a ephemeral supabase instance is bloat its in beta right now, and i'm using our gcp credits to bankroll this, so its free. the eventual pricing will be something like $/instance second and more cost effective than branching or self hosting/maintaining a supabase cluster. would love to get your feedback if you use supabase, and if you think there's something better that would fit your local coding agent setup. Thanks! https://supapool.io/ July 29, 2026 at 09:34PM

Show HN: Capitolisation – Trade like the bests elected officials https://ift.tt/Qdy8iCT

Show HN: Capitolisation – Trade like the bests elected officials Elected officials tend to overperform S&P500. The goal is to show disclosures to detect trends. https://ift.tt/GMvUWqz July 29, 2026 at 10:52PM

Show HN: Vyne – Zapier for DeFi users, run from any LLM or the workflow builder https://ift.tt/p45Gd3k

Show HN: Vyne – Zapier for DeFi users, run from any LLM or the workflow builder https://ift.tt/HZAJCa0 July 29, 2026 at 01:01AM

Show HN: Verifiable receipts for firmware CVE reproduction https://ift.tt/cU3qAfO

Show HN: Verifiable receipts for firmware CVE reproduction https://ift.tt/RhklpQs July 29, 2026 at 12:53AM

Show HN: Beakdown – a game inspired by Joust/Skirmish https://ift.tt/l9UyNuJ

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 28, 2026 at 11:48PM

Show HN: FileForge Finder: Local file search with AI-optimized export https://ift.tt/gk7AYMs

Show HN: FileForge Finder: Local file search with AI-optimized export Hope this sparks some conversation. Interested to get the community's take on an app we use internally to find files and provide targeted file content to chatbots. Biggest gains in search are for windows users but I am interested to get feedback from the spotlight users. With the AI export we originally used and MCP connector but when back to drag and drop export of file content due to security and universal applicability. No worries about your file security. Everything runs on-device and works offline. One click download at fileforge.com. Open to any feedback. Brent July 28, 2026 at 02:38AM

Show HN: Full complex text shaping and rendering on ESP32 with 320KB usable RAM https://ift.tt/hEyOdz5

Show HN: Full complex text shaping and rendering on ESP32 with 320KB usable RAM https://ift.tt/WXUFAOD July 28, 2026 at 12:18AM

Show HN: A 538-style dashboard for upcoming Knesset elections https://ift.tt/10UORna

Show HN: A 538-style dashboard for upcoming Knesset elections https://ift.tt/38S2ACf July 27, 2026 at 11:04PM

Show HN: GG Translator – Turn gaming shit talk into friendly phrases https://ift.tt/ULAhtxQ

Show HN: GG Translator – Turn gaming shit talk into friendly phrases Flaming teammates usually results in them cooperating even less. But sometimes you just need to let the devil out of you. Instead of venting on your teammates and pissing them off, vent into GG Translator and it will convert your toxic message into a friendly and constructive one to share with your team. https://ift.tt/GPwxisv My background is in building web apps with Elixir and Phoenix. I made GG Translator in early 2024 to see if I could build a desktop app in a language I had never used before (Rust) with the help of AI. It was a great exercise and I found out that I could. I used Tauri instead of Electron because it has a smaller footprint. I built the app but never released it because I wasn't ready to support it. When GPT 5.6 came out earlier this month I pointed it at the old codebase and tasked it with rewriting that entire app (still in Rust using Tauri), modernizing, refactoring, and looking for any improvements that it could find. --- The app is a sneak peek of how an AI profanity filter might look like in the future. The ultimate integration would see it built into gaming platforms like Steam and PSN where it's not only transforming your speech on demand, but it's also able to transform incoming audio from your teammates into family friendly language so parents can feel better knowing their kids aren't being bombarded with slurs when they let them play online multiplayer games. I also imagine an incredible opportunity for voice licensing allowing users to pay to unlock voices of their favorite streamers, actors, athletes, and characters for a limited time. Who wouldn't want to sound like Samuel L. Jackson yelling about motherfucking noobs in their motherfucking lane? --- The biggest obstacle was code signing. I went through all the hurdles in 2024, paying for an expensive OV signing certificate and also paying for the Apple Developer program. For 2026 I decided that the OV signing certificate is a racket and I'm not going to pay for it again. I already have an Apple Developer account for another app so I didn't have to pay extra to sign the macOS build. For Windows, the SmartScreen warnings when installing the app are a drag, but you can just tap more info and install it anyway. https://ift.tt/GPwxisv July 27, 2026 at 02:23AM

Show HN: Discrete6502 – one thing led to another https://ift.tt/bM7Rrue

Show HN: Discrete6502 – one thing led to another Disclaimer, I have not yet placed the order. But JLCPCB have so far excepted all files and config so I have 1 more button to press. If anyone see some obvious mistake please send feedback. This project grew out of curiosity. Loved the https://ift.tt/8nPce5q project but that is on another level. Here I tried to stay "reasonable" and added a Raspberry Pico 2 W on the back to drive it all. But also, was curious if Claude could pull this off. Guess I will have to place that order to call the cards. https://epatel.github.io/discrete6502/ July 27, 2026 at 01:58AM

Show HN: Infinite Jigsaw Game https://ift.tt/HikLRyh

Show HN: Infinite Jigsaw Game Had the idea forever, finally got it working. https://ift.tt/8ajLKX2 July 27, 2026 at 12:01AM

Show HN: Minesweeper Raycasted https://ift.tt/9Mldk4u

Show HN: Minesweeper Raycasted https://ift.tt/mvdXywU July 25, 2026 at 11:39PM

Show HN: Proxmox -> Share your host's Bluetooth with a VM over the network https://ift.tt/BuX3iEV

Show HN: Proxmox -> Share your host's Bluetooth with a VM over the network https://ift.tt/f87rbUa July 25, 2026 at 11:41PM

Show HN: Sourceminder.org - token-efficient code search https://ift.tt/M7dQysT

Show HN: Sourceminder.org - token-efficient code search Hey HN, The code indexing tools released in December now have added capabilities (Rust, Perl support), better token efficiency, easier install method, and a website! The website has a wasm port of the query tool, qi, so you can try it out in the browser. Let me know what you think. Thanks! https://ift.tt/3XrZQJD July 24, 2026 at 08:58PM

Show HN: A representation of a chapter of your life through music https://ift.tt/riU8Adt

Show HN: A representation of a chapter of your life through music https://www.cuecard.live July 24, 2026 at 09:52PM

Show HN: Advanced Coffee Search Covering Over 17,000 coffees https://ift.tt/50JqN1K

Show HN: Advanced Coffee Search Covering Over 17,000 coffees https://ift.tt/jTHiady July 24, 2026 at 01:29AM

Show HN: Notebooker.ai – NotebookLM alternative, your own models, keys, storage https://ift.tt/DF0zQsG

Show HN: Notebooker.ai – NotebookLM alternative, your own models, keys, storage Hi HN. This is a personal side project I've been building for about six months on top of the open-source Open Notebook platform ( https://ift.tt/NVx0Ljv ). Notebooker saves the stuff you'd otherwise lose in tabs and bookmarks - links, PDFs, audio, video - and makes it useful later: chat with a notebook and get answers that cite the exact source, turn a reading list into a podcast episode (private RSS feed, works in any player), or generate study material from your own sources. The part I've had the most fun with is a plugin engine for creation types - flashcards, charts, infographics, mindmaps, textbooks, essays, slideshows, timelines, wikis are each plugins, and new ones can be added without touching the core. Everything I've built on top of open-notebook has either been submitted upstream as PRs or is open source at https://ift.tt/KAe5Nci . Decisions this crowd might care about: - Bring your own AI keys (OpenAI, Anthropic, local/OpenAI-compatible endpoints) or use the built-in defaults. I enjoy testing Cloudflare Worker AI models. Nothing you save is used for training. You can deploy you own OpenAI compatible endpoint to play with at https://ift.tt/zFBT5DC - Bring your own S3-compatible storage (R2, Spaces, AWS) if you want your files in a bucket you control. - Webhooks in and out — anything that can POST JSON can trigger a workflow, and workflows can POST anywhere. Notebook also processes incoming RSS feeds and generates its own - Export everything or delete your account with a click. There's a view-only demo notebook at https://ift.tt/IM6Rxjw . Happy to answer any questions. I'm expecting some hiccups in releasing, feel free to report bugs or feedback. https://notebooker.ai/ July 23, 2026 at 11:02PM

Show HN: Trifle – Open-source analytics that stores answers, not events https://ift.tt/NSs9B4j

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 06:39PM

Show HN: LiquidBrain – Unlimited Tokens. Unlimited Context. One Fixed Price https://ift.tt/lorKNI1

Show HN: LiquidBrain – Unlimited Tokens. Unlimited Context. One Fixed Price https://liquidbrain.ai/ July 23, 2026 at 12:59AM

Show HN: The Daily FM – Turn any source into a daily podcast https://ift.tt/SM7UNoL

Show HN: The Daily FM – Turn any source into a daily podcast I built The Daily FM because I wanted a daily summary of the latest AI news sent to my podcast app and then realized it was useful in summarizing other stuff: - Any blogs, websites, or X handles - The top Hacker News stories with comments - Long podcasts (think Lex Fridman) - Changes in state/federal legislation It pulls your sources, writes a script with a frontier-ish model of your choice, runs it through TTS (MAI-2 studio voices), and publishes a standard RSS feed. You can also combine several pods into one feed for one subscribe point. Under the hood it’s using Cloudflare Workers, queues, browser rendering, and the AI Gateway, but the TTS models aren’t very good on Cloudflare so I switched to the MAI-Voice-2 models with OpenRouter. I also created a public library you can subscribe to without ever signing up, or if you sign up, you can combine a bunch into a single feed and use your own sources as well and choose from other voice options if you don’t like “Excited Ethan” at 1.1x speed. Feedback welcome. https://thedaily.fm/ July 23, 2026 at 12:50AM

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

Show HN: Szr: A safer command output reduction for coding agents https://ift.tt/hf6EgPm July 22, 2026 at 10:03PM

Show HN: DocCharm – The help center that keeps itself up to date https://ift.tt/W6x5LFI

Show HN: DocCharm – The help center that keeps itself up to date Hello HN! We were finding it too much work to keep our Zendesk help center up to date as our product kept changing, so I built DocCharm — it keeps a help center up to date automatically by watching PRs as they land in your GitHub repository. It suggests updates (with AI) to existing articles, or drafts entirely new ones if nothing appropriate exists yet. Everything goes into a review queue first, so a human always checks (and can optionally edit) before anything publishes. In practice this has proven to be a pretty slick workflow (in my opinion anyway, but not only!). We’ve been using it at my main job for a while now and it’s a big time saver. It’s also gaining some traction with other companies in the same investor portfolio. My sales process so far has been high-touch outbound. This probably won’t scale in the long run, but I’m hoping to learn as much as I can by nurturing all of the initial relationships. If you run a business with a help center that’s drifting out of date, email me and I’ll comp your first couple of months. Email is in my HN profile. Both Zendesk and Mintlify help centers can already be automatically imported into DocCharm. If you use a different help center, let me know and I’ll get it automatically imported one way or another. I've also implemented some support for theming, so you can keep your own branding. The tech is essentially the same that I use for most of my work (and it's not a differentiator, but we're all tech-curious here): - Haskell/Yesod - NixOS - SQLite with Litestream (db per tenant; backed up on both Hetzner and Cloudflare; encrypted) - Sentry for error reporting - Stripe for billing - Healthchecks.io as a dead man’s switch - Prometheus and Grafana for telemetry - Resend for transactional email There's plenty still to do on the roadmap, but this is already working nicely and providing value as is. I'm not building in the open, though what I prioritise will naturally be heavily guided by the needs of the earliest users. WDYT? https://doccharm.com/ July 21, 2026 at 09:34PM

Show HN: Immersive Gaussian Splat tour of grace cathedral, San Francisco https://ift.tt/afuQmsl

Show HN: Immersive Gaussian Splat tour of grace cathedral, San Francisco https://ift.tt/ROiLhmI July 21, 2026 at 12:10AM

Show HN: cbxy – A format for creating guided comic book experiences https://ift.tt/4zMhQYF

Show HN: cbxy – A format for creating guided comic book experiences https://ift.tt/GTADROk July 20, 2026 at 10:56PM

Show HN: ShipMD.app – Moving things in folders, move things in the real world https://ift.tt/dKuPIlr

Show HN: ShipMD.app – Moving things in folders, move things in the real world https://shipmd.app July 20, 2026 at 01:09AM

Show HN: A canvas-based note taking and organizer app https://ift.tt/kRvq9lC

Show HN: A canvas-based note taking and organizer app So I've been working on this app for a very long time now. Started off by wanting an app that separates long form notes from short form notes visually and keeps everything organized on a canvas. The app features: -Sticky notes for quick, small notes and A4 notes for long form documents -A quick mode that uses local storage to quickly open the app and jot down a thought on the canvas -A PDF export option that exports your notes into 3 custom designed PDF styles -Visual hierarchy to replicate file structure instead of a linear fashion, where your files are notes, stacks are folders and labels are names for your folders Would love to continue working on this app if you guys like the concept. https://ift.tt/PrciMCk July 20, 2026 at 01:31AM

Show HN: A gallery of browser-based PDF imposition and printing templates https://ift.tt/ojtd6bC

Show HN: A gallery of browser-based PDF imposition and printing templates https://ift.tt/5Ya9rKF July 19, 2026 at 09:46PM

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

Show HN: Chalie – AI peer not employee https://ift.tt/q1gOkNS July 19, 2026 at 11:34PM

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

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/vREiSfN 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/i7hcZ36 July 19, 2026 at 02:54AM

Show HN: RewindCup – explore 23 World Cups on an interactive globe https://ift.tt/Dvm6nGQ

Show HN: RewindCup – explore 23 World Cups on an interactive globe https://rewindcup.com July 19, 2026 at 02:07AM

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

Show HN: Peek-CLI: Let Claude Code iterate on front end designs https://ift.tt/16Papwd July 18, 2026 at 11:02PM

Show HN: SDF Pelicans on Bicycle https://ift.tt/k5avzAd

Show HN: SDF Pelicans on Bicycle https://ift.tt/1cgZ5Aq July 18, 2026 at 11:17PM

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

Show HN: Tools Berry – client-side calculators with open-source tax engines https://ift.tt/axBjqTf July 17, 2026 at 11:38PM

Show HN: Lific: Issue trackers should be simple, right? https://ift.tt/IGdp8SX

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 09:52PM

Show HN: Rudo - A small, elegant dock for Wayland https://ift.tt/rG0As98

Show HN: Rudo - A small, elegant dock for Wayland https://ift.tt/KjQ4eAm July 16, 2026 at 11:42PM

Show HN: SirixDB 1.0 Beta – Git-Like Versioning, Diffs, Time-Travel Queries https://ift.tt/iVUI4nT

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/41ybZTl ) and again in 2023 ( https://ift.tt/DOQJ5VF ). 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/YWOJqM6 [2] https://ift.tt/GiDajnu [3] https://demo.sirix.io [4] https://sirix.io/docs/ [5] http://brackit.io https://ift.tt/YWOJqM6 July 15, 2026 at 07:46PM

Show HN: Leet Robotics: Learn robotics and ROS2 with hands-on courses https://ift.tt/nj3AyM7

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/576jHCO July 15, 2026 at 04:14PM

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

Show HN: Beautiful Type Erasure with C++26 Reflection Try it on Compiler Explorer: https://ift.tt/EL8jZld Check out the source code: https://ift.tt/Vb7ik4K https://ryanjk5.github.io/posts/rjk-duck/ July 14, 2026 at 04:40PM

Show HN: A device for never missing the surf turned into something more https://ift.tt/s3mYyFN

Show HN: A device for never missing the surf turned into something more https://ift.tt/yQmNG7p July 14, 2026 at 11:12PM

Show HN: I implemented a neural network in SQL https://ift.tt/kfVu0q5

Show HN: I implemented a neural network in SQL Two weeks ago I was on my babymoon in Corfu, Greece. While in transit, I was overseeing a GSoC intern submit an important feature to my array database library, Xarray-SQL. He added `to_dataset()`, which completed the roundtrip between thinking of array data in a tabular model simultaneously as gridded rasters (the premise of the project is that every Nd array can be mapped to 2d, where orthogonal dims of the Nd array are just primary keys of a tabular representation). We discussed in chat, now that this feature existed, what demos could we make that would prove this data model works? With down time on a warm beach during a heatwave, cool salty water giving me fresh ideas, I had an idea: what if we used Coiled's Geospatial benchmark discussion as a comprehensive overview of geo and climate queries. Are all of these common operations secretly relational, just with the wrong data model? Using Claude Code on the beach, I can confirm that this seemed to be the case: Claude and I publish a benchmark that illustrated how every common operation in geo and climate sciences (at the 100 TB range) were actually secretly relational operations: https://ift.tt/obL5FXw... . Most surprisingly of all, from these examples was that a core operation, regridding, was just a sparse matrix-vector product. Claude had pointed out to me that in this data model, matmul was just a `SUM(val * val) ... JOIN .. GROUP BY`. This has a direct parallel to einsum notation, but can be expressed in (arguably) elegant SQL syntax! This capability seemed to be greater than the sum of it's parts. Back in the cool water of the Ionian, I thought about the implications of this more deeply. I reflected that, all of the Coiled benchmarks did, deep down, was _post process_ simulations that happen in numerical/array code. Why couldn't these physics calculations be push down into the database also, if we could so matmul in SQL? Then it hit me: maybe they could, if in addition to linear algebra, if SQL could do calculus! https://ift.tt/xtmFzHT Later on, I implemented autograd on top of DataFusion's visitor pattern based on JAX's implementation. In my simplified array model, it turns out that we only care about partial differentiation on the diagonal of the Jacobian, meaning that `grad()`, `jvp` and `vjp` are just row-wise operations! I then implemented a common physics calculation from the coiled benchmark that required gradients. From here, I realized if I can autograd in the database, why can't I create a neural network? As I came back home, I created some slides, and presented this work to DataFusion's inaugural showcase: https://www.youtube.com/watch?t=1511&v=5o-4hL8vGPw&feature=y... I realized in this synthesis that SQL is not necessarily a toy language for writing neural networks, but in fact, may be highly desirable in the future due to the fundamental principles of relational databases: the logical layer should be independent from the physical layer. If that property holds, and a neural network is a series of relations, could we create a SOTA distributed system for training more easily? For example, if we had one global logical plan of dataflow, could we better distribute work on 1000+ GPUs? Several scientists and engineers and I are working together to explore this weird world of relational arrays at https://xql.systems (discord link at the bottom if you want to get involved). https://ift.tt/MWQGZod July 14, 2026 at 12:00AM

Show HN: PlanWright – A control plane for AI coding agents https://ift.tt/QqYaRXr

Show HN: PlanWright – A control plane for AI coding agents MCP driven control plane for Agentic Engineering. Plan from Claude Desktop, implement in Codex, review in a custom triage agent. All via MCP, all logged and tracked with full documentation of all decisions made by each agent. https://ift.tt/RJhroKs July 13, 2026 at 11:59PM

Show HN: Scramble Quest https://ift.tt/xIHXB9R

Show HN: Scramble Quest https://ift.tt/b61aSNq July 12, 2026 at 09:58PM

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

Show HN: Sqlsure – deterministic semantic checks for AI-generated SQL https://ift.tt/9pyPlH7 July 12, 2026 at 12:03AM

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

Show HN: Don't let your engineering brain rot in the age of AI https://ift.tt/vHLAY0m July 11, 2026 at 11:57PM

Show HN: Share and explore custom Claude Code status lines https://ift.tt/Rc9oInM

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 11, 2026 at 11:51PM

Show HN: We beat Cloudflare's bot detection (open-source stealth browser) https://ift.tt/rKc3uHO

Show HN: We beat Cloudflare's bot detection (open-source stealth browser) https://ift.tt/3mJuSU5 July 11, 2026 at 04:26AM

Show HN: SubjectiveZero, an open-source agentic node editor for creative coding https://ift.tt/x1HLIVZ

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/dPt5Xlw https://ift.tt/dPt5Xlw July 10, 2026 at 07:23PM

Show HN: Wyrm – Solve algebra by touch, built on an open-source soundness engine https://ift.tt/noeCx1w

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/hXMEk4j ) and as of this week on Google Play ( https://ift.tt/2iywdZI... ). I also decided to open source the underlying math engine so others could build on it: https://ift.tt/ygtdXIL . 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/ygtdXIL July 9, 2026 at 03:16PM

Show HN: Pylon Sync, an agent-first full-stack realtime framework https://ift.tt/8NAPYi2

Show HN: Pylon Sync, an agent-first full-stack realtime framework I created Pylon to make it easier to move from hobby projects to full production apps. When I work on hobby projects, I usually use React or Next.js because they are quick to set up and easy to deploy on Vercel. For production apps, I separate the frontend and backend, then deploy the backend on AWS. But setting up a full backend on AWS can be complex and costly, especially for simple apps. Pylon is a full-stack, real-time framework that includes server-rendered React, TypeScript functions, entities, policies, real-time sync, built-in authentication, and support for background and scheduled jobs. By default, it uses SQLite, but you can switch to Postgres for production. The authentication system is heavily inspired by better-auth. The runtime is a Rust server that runs TypeScript functions and server-rendered React using Bun. Pylon itself is inspired by Rails and focuses on convention over configuration, so you have fewer decisions to make before deploying. This approach applies to modern React apps, real-time sync, TypeScript server functions, authentication, job management, and deployment. One of Pylon’s main goals is agent compatibility. It lets coding agents build and deploy apps with no setup, quick understanding, secure defaults, and easy deployment, all without requiring any third-party services. Pylon works for both quick projects and production apps where performance, observability, ownership, and self-hosting matter. While it’s easy to self-host Pylon apps, Pylon Cloud provides managed hosting with a developer experience similar to Vercel. You can deploy from git or the CLI, get an instant URL, add custom domains, and go live in seconds. Each app runs on its own server, which can scale to zero, with TLS and global caching enabled. If you have experience with Next.js, Vercel, Convex, Supabase, Firebase, better-auth, or Rails, I’d love to hear your feedback. Create your first app: npm create @pylonsync/pylon@latest Website: https://ift.tt/ASyXz4N Repo: https://ift.tt/wRbXkjs Docs: https://ift.tt/vU0KrC4 LLMS: https://ift.tt/xuzi65y Skill: npx skills add pylonsync/pylon Examples: https://ift.tt/IuLUKB1 https://ift.tt/ASyXz4N July 9, 2026 at 09:38PM

Show HN: Policy enforcement for Claude Code, Cursor, and Codex https://ift.tt/GyOT9sF

Show HN: Policy enforcement for Claude Code, Cursor, and Codex Show HN: Runtime authorization for Claude Code, Cursor, and Codex Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. This is aimed at developers using coding agents like Claude Code, Codex, Cursor, and OpenClaw. We built Kastra after one of our Cursor agents almost executed DELETE FROM customers WHERE status='test' against a production database. We caught it before it ran, but it made us realize that nothing in our stack actually decided what the agent was allowed to do. What mattered for us wasn't the mistake; it was realizing nothing in our setup would have stopped it if we weren't actively on top of it. LLMs are probabilistic, and prompts influence behavior, but they don't deterministically decide what an agent is allowed to do. Without a deterministic policy system, nothing could have decided what it was allowed to do. Kastra pushes an allow, hold, and deny decision before the action runs. You can build these policies in plain English from the web app. The interception engine evaluates the tools, targets, and parameters of every action. We also shipped many policy packs covering common high-risk scenarios, and every decision is recorded in an immutable audit trail. The desktop app, CLI, dashboard, and Recon scan are free to use for developers. If you often use Claude, Codex, Openclaw, and Cursor, Kastra can run a scan command on which risky actions your agents have already taken and automatically build rules to avoid them from happening again. Recon is a feature of Kastra that scans your local agent history. In order to run this scan, execute the commands below in your coding agent. brew install kastra-labs/tap/kastra-edge kastra-edge scan The scan reads your local agent session history, and it shows all the risky actions your agent has already taken before, the secrets written to tracked files, production databases touched, force pushes, curl-to-shell, and more. This runs on your machine, and secrets never leave. In our own use cases, we kept finding things we'd forgotten or didnt know agents had done. Each finding can be converted into a runtime policy, letting you delegate more work to AI without trusting the model itself. Kastra intercepts all workloads at runtime and makes sure these policy evaluations typically complete in under a millisecond. Instead of trusting the model, you trust the deterministic rules that govern its actions. One problem we are still working on to improve the stack is how to manage teams of agents with conflicting policies. We would love feedback from anyone building multi-agent systems. Fernando and I will be reviewing the comments. We are super curious what your first scan finds. Please post results below so we can see what the most common patterns are and adjust policy packs for our users based on your feedback. Documentation: https://kastra.ai/docs Download for MacOS Kastra Edge: https://ift.tt/6fq8Fge Check Kastra in action today: https://www.youtube.com/watch?v=6TUETu5lb3Q&feature=youtu.be https://kastra.ai/ July 9, 2026 at 07:26PM

Show HN: Getting GLM 5.2 running on my slow computer https://ift.tt/QtcO9f7

Show HN: Getting GLM 5.2 running on my slow computer A few days ago I found myself trying out GLM 5.2 and was really positively impressed. 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. I just 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! (and if anyone wanted to participate in the project I would be delighted) Repo: https://ift.tt/PMSBqRx https://ift.tt/PMSBqRx July 9, 2026 at 12:05PM

Show HN: EVconomics – EV vs. gas cost-of-ownership calculator with live prices https://ift.tt/C7NVZs6

Show HN: EVconomics – EV vs. gas cost-of-ownership calculator with live prices https://ift.tt/EGkHATl July 9, 2026 at 11:29PM

Show HN: Onboard-CLI, a LLM powered and AST-based tool to visualize codebase https://ift.tt/Ap03trd

Show HN: Onboard-CLI, a LLM powered and AST-based tool to visualize codebase https://ift.tt/I3JzxYt July 9, 2026 at 12:09AM

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

Show HN: Skill-extractor turns coding agent transcripts into reusable skills https://ift.tt/czvlwK1 July 9, 2026 at 12:03AM

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

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 12:00AM

Show HN: REST - Living Without Burnout. A manifesto about sustainable discipline https://ift.tt/2crsx45

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 8, 2026 at 11:42PM

Show HN: CLRK, an open-source agent runtime with gVisor and MitM guardrails https://ift.tt/svxomWr

Show HN: CLRK, an open-source agent runtime with gVisor and MitM guardrails TL;DR: we built a framework-agnostic agent runtime that uses gVisor for isolation and runs on k8s. It’s open-source under AGPLv3 Recently we’ve been working on a customer support “AI assistant” - essentially an interactive knowledge base/L1 support but with an option to touch resources that belong to a customer it’s talking to. We found existing tools to be lacking in these aspects: 1. Fully intercepted i/o. We wanted to trace out LLM calls as well as any other networking calls attempted by the harness so that guardrails and audit trails apply to all current and future systems uniformly. Nobody’s agent can accidentally make raw database calls or send PII data to an overseas LLM provider. 2. Coherent API and framework agnostic. There’re a lot of frameworks out there that do similar things in slightly different way and most we found had telemetry, guardrails and other tooling tightly bound into the framework. We wanted something with an infrastructure-first approach because we think it’s a more flexible way to compose such systems. 3. k8s compatible runtime. We run part of our stack on k8s and know it well so we wanted to take advantage of this if we could. We searched for an existing solution, but especially with Daytona going closed sourced recently, there were no options we could find that were open-source and met our needs, so we built one. A more in-depth design writeup can be found here: https://ift.tt/uWxbMQn Questions, FRs, hot takes or funny insults are welcome! https://ift.tt/rAjmNfg July 7, 2026 at 11:45PM

Show HN: Halo – open-source, tamper-evident runtime evidence for AI agents https://ift.tt/L9JGeMA

Show HN: Halo – open-source, tamper-evident runtime evidence for AI agents Hi HN, I'm Brian, I spent the last few years at Vanta (YC W18), helping startups and enterprises become compliant and I recently started exploring what that might look like in a post-agentic world. The problem Halo solves is: when a company buys an AI agent from a vendor and gives it access to their data, they have no way to check what the agent did with that data. Vendors may have built observability dashboards and audit logs, but those are editable and partisan. SOC 2 and ISO 27001 audit a company's controls, but controls are less predictive when the software is agentic. TLDR: give an agent the same prompt 50 times, and you get 50 slightly different actions/answers - so the only thing worth auditing in a post-agentic world is what happened at runtime. Halo is an open-source project that produces agent runtime evidence. It's a small recorder that records every action an agent takes (eg. tool calls, model calls, data access, etc), and becomes a record in an append-only log. It's hash-chained, so anyone can re-verify. Run the following command to see a fictional example: uvx --from halo-record halo demo --serve Then, delete a line from one of the .jsonl files and reload, and the report will catch that it's been tampered with. To wire up your own agent, run this line of Python: agent = trace(run_my_agent, profile="my-agent", log="audit.jsonl") Then use this to generate a real report and give it to your customers: halo report audit.jsonl -o report.html Disclaimer: this proves integrity, not completeness (as a self-held chain proves nothing was edited but does NOT prove that nothing was omitted). Catching this requires a witness outside the vendor and is what I'm working on next. Halo is Apache-2.0, contains zero runtime dependencies, and is about 4,300 lines of Python with 125 tests (if you prefer TypeScript, here's that repo: https://ift.tt/IbjQTE7 ). Give it a try, and please let me know if you have any feedback! https://ift.tt/7t9W4wb July 7, 2026 at 06:07PM

Show HN: Dike is a compliance gateway for AI products in the EU https://ift.tt/iU1Pkg3

Show HN: Dike is a compliance gateway for AI products in the EU https://d1k3.com July 7, 2026 at 12:46AM

Show HN: orzma – a terminal emulator that renders webviews inside the terminal https://ift.tt/2EozUg8

Show HN: orzma – a terminal emulator that renders webviews inside the terminal I made this because I thought it would be useful to be able to use a webview in the terminal. I also provide an SDK called ratatui_orzma. For example, I think it could be used to render rich UI components such as charts with a webview as part of a TUI application, port web tools to ratatui, or embed games built with Wasm inside the terminal. https://ift.tt/8AvNoka July 6, 2026 at 11:20PM

Show HN: Social and context-aware AI platform to do math https://ift.tt/KxE4rlM

Show HN: Social and context-aware AI platform to do math Hi HN, This is ProofTree, and in TLDR: it is a platform where you can chat with an AI to do math, the way you already do, with context-awareness and knows how you personally do math, connected to the fora of other live human mathematicians. So, when you are talking to an AI about a proof at 3 am, and you need a human expert looking at it, or a discussion around it, like you do on StackExchange, this is it! You need an approved email account to use it, so please write here if you would live to try it out. https://ift.tt/me5lb7v July 6, 2026 at 12:06AM

Show HN: Osint tool that finds exposed files on domains https://ift.tt/i8AguaF

Show HN: Osint tool that finds exposed files on domains hey guys, wanted to show one of my side projects i just made public. the idea is basically another osint tool for pentesters and bug bounty hunters. it watches certificate transparency logs and checks newly-seen domains for exposed stuff like .env files, open .git dirs, config files, db dumps and so on, and puts whatever it finds into a searchable db. you just search a domain (or part of one) and see what's exposed. it's read-only and free. one thing i've been thinking about adding is a way to register for certain keywords and get notified when something new shows up for that search. would love to hear if you have other ideas for useful features, and also ideas for how to reduce abuse of the data, since that's the part i'm least sure about. https://ift.tt/J0SZCn2 https://ift.tt/J0SZCn2 July 6, 2026 at 12:24AM

Show HN: Meon – declarative flat-parsing engine (SoA, no AST) https://ift.tt/cMNjsg8

Show HN: Meon – declarative flat-parsing engine (SoA, no AST) https://ift.tt/ANGIb6K July 5, 2026 at 09:43PM

Show HN: I built an encrypted BLE dongle for pasting stuff to air-gapped devices https://ift.tt/ZbKY7G3

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/PuEqtkY July 5, 2026 at 01:13AM

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

Show HN: Gemma 3 inference in pure C++ with Metal acceleration https://ift.tt/InLSz8D July 4, 2026 at 07:54PM

Show HN: Topics, Not Feeds https://ift.tt/nIORZyY

Show HN: Topics, Not Feeds https://blogsreader.com July 3, 2026 at 11:49PM

Show HN: Kontext – Move an AI chat's full context to another AI in one click https://ift.tt/c6G30TS

Show HN: Kontext – Move an AI chat's full context to another AI in one click https://ift.tt/OwkLerB July 3, 2026 at 11:27PM

Show HN: Auto-continue Claude Fable 5 the second your 5-hour limit lifts https://ift.tt/3LNhau1

Show HN: Auto-continue Claude Fable 5 the second your 5-hour limit lifts https://ift.tt/otlaTyZ July 3, 2026 at 11:35PM

Show HN: A provider-agnostic agent loop built on ports and adapters https://ift.tt/t0NCJor

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/VGq4Aw0 July 2, 2026 at 11:22PM

Show HN: PurRDF-High performance, cross platform RDF1.2 https://ift.tt/bkufVNF

Show HN: PurRDF-High performance, cross platform RDF1.2 https://ift.tt/btAgfO3 July 2, 2026 at 11:15PM

Show HN: Inkwell – An RSS reader for e-ink devices https://ift.tt/SfEya9c

Show HN: Inkwell – An RSS reader for e-ink devices https://ift.tt/7iLam5s July 2, 2026 at 07:38PM

Show HN: Salt – a systems language with Z3 theorem proving in the compiler https://ift.tt/xPTKle1

Show HN: Salt – a systems language with Z3 theorem proving in the compiler https://salt-lang.dev July 1, 2026 at 09:05PM

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

Show HN: Searchable directory of 22k+ products from worker-owned co-ops https://ift.tt/XYL7wbA July 2, 2026 at 12:47AM

Show HN: Z-Jail – A 130 KB Linux sandbox-C99 with 7 defense layers and zero deps https://ift.tt/iB9UeXn

Show HN: Z-Jail – A 130 KB Linux sandbox-C99 with 7 defense layers and zero deps https://ift.tt/WhyG0Np July 1, 2026 at 11:18PM