Launching https://leafy.you soon - a general-purpose in-browser assistant. Compiles reports, fills forms, interfaces with 900+ services you own.
More broadly, I spent ages developing a self-solving Kanban for mid-sized companies and enterprises (kodan.dev) - controllable autonomy level, multiplayer support, remote coding server, *works on multirepo projects*, mobile support, previews, and more. The pain exists, but it's pretty hard to break the integration barrier.
So I'm spinning the feature I used the most into a separate, easy-to-understand product for now.
I'm working on a general repo shape/structure linter (language agnostic)[0] - the idea is to enforce things like directory structure, existence of various files (LICENCE, etc.), file naming patterns, jsonpath + schema over json/yaml/toml, absence of potentially malicious unicode. It comes with rule bundles for various languages/presets which can be combined and extended. A goal is for it to be very fast, and useable on huge monorepos. I noticed myself having to add various forms of validation/scripts when coding using AI, and decided to build a reusable, fast tool for this purpose instead of rolling validation scripts for each project.
I'm working on rookery, "A PGP-first, self-hostable email server that comes with a web mail client and modern standards out-of-the-box.": https://github.com/oleblaesing/rookery
If you are a privacy minded person like me, you got only a few options when it comes to email with some ease of use: ProtonMail, Tuta etc. Rather than becoming a new competitor to those, I want to give the power of the decentralized email standard back into the users hand. Everyone with a bit of self-hosting/Linux knowledge, can setup their instances for themselves and their friends/family/business.
Bootstrapped that heavy via vibe coding. Used it to learn a lot about the email standard and related technology. However, I find it too valuable to just be a learning project. Now I'm cleaning it up to get in control again and to proof its secureness by rewriting/restructuring/refactoring line by line.
Two months ago I went full time on my indie game after just under a year and a half of part time work. I’ve been prototyping in Godot for about 6 years now, and finally had a game that my business partner and I were really interested in and felt matched the current market desires. It’s cozy world builder, drawing inspiration for Sim City, Rollercoaster Tycoon, The Sims, with an aesthetic influence of Stardew Valley, Animal Crossing, and the like.
This was very much a passion project and an idea I’ve wanted to see alive for decades, and also let me explore some tech I wanted to get deeper on. I’m bullish on the the tighter integration of CPUs, GPU style cores, and shared memory. Our game, LocoMo, relies heavily of GPU processing of entities under the hood.
After 1.5 years of development and two exhausting pivots, I’m incredibly happy to finally have our v1 live!
While most of the HR tech is rushing to use black-box AI, I built the exact opposite. It's a transparent, math-driven fitness engine. It extracts objective data from CVs and calculates how well applicants match requirements, letting you see the reasoning behind why someone scored an X%.
If anyone here builds in the HR space or regularly hires engineers, I would absolutely love your feedback or a roast of the landing page.
PS This is a project of immense importance for me, I've been working on for past ~2 years, I'd appreciate to know why this comment is flagged.
As someone who worked on HR Tech in 2024-2025, I think you're really solving a problem here. Cat is out of the bag already it's not like HR can go back to the pre-AI world ... I'm also puzzled by the flags. Congrats on your project :)
flags or downvotes probably come from people being skeptical about automated CV evaluation. in europe this is also legally questionable.
also matching requirements should be secondary to experience. someone who has done a few react websites will not be as qualified for your react job as someone that has done 10 years of angular and vue and can learn react in a short time.
I continue to work on my city builder game Microlandia, launched here in HN ~6 months ago. I originally predicted a few dozen urbanism nerds would play it, but now almost 10,000 copies sold. I'm still a solo developer but now I collaborate with 2D, 3D and music artists. Which is good because the original art that I drew myself for the launch was horrible.
I'm currently working on modeling energy, climate and new policies like universal basic income
Man looks amazing, the detail level of the simulation seems to be in another level compared to sity skylines and co.
If you need any help or just chat about this, reach out to contact (At) khorchani (dot)fr
Still plugging away at Breaka Club, where kids take photos of their hand drawn art and build games using it. Starts out as no-code, photograph an AprilTag and it imbues the image with functionality.
I'm running an in school pilot this week (Lunch time school club).
The tech stack for the main product is honestly pretty intense at this point with full multiplayer support, offline play, transitioning from client authoritative to joining a remote server. Built atop GodotJS, TypeScript bindings for Godot, which I maintain. Huge monorepo with over a million lines (yes, I'm aware that's NOT a good thing), and GodotJS itself is not included in that.
I'm finally fulfilling a childhood dream of restoring a Heathkit oscilloscope. I managed to nab a functioning IO-12 at the thrift store for $75!
Don't tell my husband that I spent more than $200 on parts and supplies for it.
I've wanted a Heathkit since I learned about them as a teenager, and this is the first one I've ever seen in the wild. The original owner left the date he assembled it and his callsign written on the inside! I looked him up and he died in 2013, but by sheer happenstance I'm restoring it 58 years to the day that he initially built it. I got super lucky with this unit because as far as I can tell, it's only been run a few hours in its entire life. I really only have to replace aged components because they're physically breaking down, I expect the thing will outlive me once I'm done with it. Can't wait to hand it off to a bewildered young EE in another half century.
The last few months I’ve been reading a lot about neuroscience behind learning and practicing music and I’m fascinated by the subject. It has helped me realise why the app works for me, as well as my own mistakes that held back my progress for many years despite putting in decent efforts.
It was a much needed inspiration to continue working on it with a re-evaluated roadmap.
After getting the top spot in What Are You Working On in Feb 2025 ( https://news.ycombinator.com/item?id=43157056 ) I started a company on that idea at https://getcomper.ai . After solo building for 11 months I found a co-founder, got an angel investment, then got some ex-Miro folk on board and we are now building the product at breakneck speed.
We're a collaborative canvas + context engine for all the code and docs in your company, with a zoomable UI + CLI , where you can collaborate with your co-workers and agents.
We map technical debt, agent readiness, code complexity, security scanning, bus factor and more, so you can easily see how all the software in your company runs.
One of the most complex things is our incremental git blame engine built on top of GitOxide, as our backend is fully built on Rust. Our frontend is built on PixiJS so you can explore at gaming speed with 60Hz refresh rates.
Recently we sponsored Rust Week in Europe and a hundred or so developers tried our mini-game which is GeoGuessr for code, and got rave reviews. Future is looking bright!
A tide flag. As in, a mechanical device that turns a weather-vane-like flag that moves with the ebb and flow. It has to be powered by the tide, and must be able to withstand the elements. And, must look cool.
Then, I will slap an ESP32 & z-wave on it :D secretly to feed my Home Assistant. :D
Working on my version of Dynamicland. Today I got this small thing working where I can now live-edit the behaviour of the editor script, see https://www.youtube.com/shorts/ZjxPIv-XwoU
I’ve been playing D&D for a few years with friends, and over time we’ve built a rich world..full of contradictions because I can’t remember half of the improv I do as DM.
I built https://loracle.app to automatically build a wiki of various entities in our campaign and enable rag q&a with an ai assistant about specific world facts.
My wife and I are working on a math/science/CS-inspired jewelry business.
We try to create pieces that stand on their own aesthetically but have a hidden meaning. We currently have two styles: lambda calculus based pieces (we depict the lambda/Tromp diagram) where we have Y-Combinator earrings (well, strictly speaking they are one beta reduction away from Y-combinator. Aesthetic oblige) and a pendant depicting a lambda expression computing Graham's number. The other style is quantum computing circuits, based on quantum computing research my brother (a physics professor) is doing: a pendant that is actually a non-local controlled-NOT gate.
I wrote a tiny DSL to describe the jewelry pieces, and an interpreter to produce CAD files. We then either 3D print them or have them produced by lost-wax.
We are 200% out of our comfort zone (and love it): I know nothing of front end dev, payments, or anything like that. The diamond district in New York is a neighborhood we normally actively avoid, but if you are forced to go there it is fascinating (people examining diamonds on the corner of the street, others in fur coats in summer straight out of a mafia movie...), and especial marketing. Jewelry is a completely saturated business (luckily we are not doing this to pay the rent); we think we have a unique angle, but we are still figuring out the target audience (if there is one).
Still working on my web site quality assurance software. Getting close to private beta (hopefully very soon). Back end is written in Java and built with Javalin and Jsoup and persisted to PostgreSQL. Front end is JS/React. My back end crawls the designated website and for each page runs a number of analyzers to assess the quality across the following categories: accessibility, content quality (spelling, missing spaces between words, etc), performance, security, content policy (required phrases and forbidden phrases), site integrity, and seo. Each site can be configured to have its own custom dictionary (for spell checking). It's been a lot of fun and I'm looking forward to taking the wraps off it.
I've continued working on Eidetica, my decentralized database project. I recently added support for a client/server architecture so that it can be transparently run as a local daemon for background sync and sharing the local storage with multiple users. I've been making progress on integrating blob storage next, as well as scoping out WASM based "lenses" for handling decentralized version/schema updates. https://github.com/arcuru/eidetica
I've primarily been testing it by building out my AI tool chaz into an Eidetica-native AI Agent framework for decentralized Agent sessions. It's working surprisingly well, it maps pretty well onto the storage model and it's uncovering issues with Eidetica I need to fix (which was always my primary reason for building it anyways). https://github.com/arcuru/chaz
Separately I'm building OptiMap, a SIMD-accelerated hashmap repo that explores the design space for hashmaps and benchmarks different approaches. This is mostly for my own learning but I'll eventually turn into a blog post. https://github.com/arcuru/optimap
My wife and I continue to work on Uruky [1], a simpler Kagi alternative, based in the EU.
Last month we launched image search (got out of beta this month), added our own index and crawler (via Uruky Site Search [2]), and reached 100 monthly active accounts (we’ve passed 150 now)! You can also see a privacy-focused independent blogger wrote about us [3]!!
You can check out the main differences between Uruky and Kagi, DuckDuckGo, SearXNG, etc. in the footer (right side), but one huge difference is that with Uruky, after being a paying customer for 12 months, you can download a copy of the source code (licensed as BUSL into AGPLv3 in 2 years — a suggestion made here in HN)!
You can also now get a free trial for 2 hours when you signup if you pass a proof-of-work captcha (another suggestion made here on HN, and it uses a local Altcha).
Our main challenge continues to be discoverability and outreach because we want to do it ethically. Ideas are welcome! We’ve been sponsoring open source projects, open source maintainers, and indie, small-web, and privacy-related websites and applications.
Feature-wise, for June we’ve already added a ton of personalization and privacy-increasing features like URL rewrites, cash-by-mail payments, and anonymous vouchers! Upcoming is partnering with ProxyStore to sell vouchers (we’re currently in talks for this), so you can buy vouchers with XMR/Monero or other cryptocurrencies. Then we’ll be looking into increasing our own index, focused on indie/small web.
Thank you so much! We would definitely love to have that happen, too! We couldn’t have imagined we’d get to 100 monthly active accounts so soon (and now past 150), but we’d need at least an order of magnitude more in order to have it be sustainable as a full time business for us.
That being said, it definitely looks possible, so we’re excited! As it stands, it’s already sustainable part-time and can go long-term.
https://mdview.io - the best way to read big technical documentations. Right now I am working on Grill Me feature for rigorously questioning and stress-testing plans or designs without leaving the app ui
I've been turning my Media Viewer into a complete local first media ecosystem for automated tagging, a media server, phone swiping, and a web version of the viewer so you can access it remotely. https://lowkeyviewer.com/
The thing Im most proud of though is just the viewer, its designed to just open all the images and videos in a folder, and then there is no UI except a right click context menu, the list is a grid or a masonry layout that uses 100% of the space for the images/video so you can just navigate them. It adds anything you open to a local sqlite db so you can tag things if you want optionally. Also control modes that make sense for either a mouse or a laptop trackpad.
I'm maintaining a public dashboard that monitors the occupancy of public parking garages in my city (https://www.parkeergaragesdelft.nl). Last year the city council requested this information from the municipality but it's still not delivered. I just finished a redesign that includes references to the relevant city council discussions that aren't settled due to missing data.
Another project is https://www.beeldplek.nl, a timelapse platform powered by community photos. The idea is to place a mount and QR code at fixed viewpoints around the neighbourhood. People scan, photograph the view, optionally add their name, and submit. The infrastructure is up and running but getting the permit to place the mount has been a slow process so far.
Mainly https://www.vaava.app/ is a baby tracking/logging app I originally built for myself, now available on both app stores. All the user generated data is stored only on device and is transferred in local network to users who you have paired the app with. There is 0 behavioural analytics, even the crashlytics are 100% optional.
There is a couple of semi-unique features; you can use your voice to dictate and generate events (feeding, sleep etc), you can also scan documents for growth measurements.
You don't need user account to use it, there is no subscription, the paid features are available behind a single purchase for lifetime. Still, like 90% of the features are available for free.
Also
https://www.athilio.com/ privacy focused, highly customisable personal data analytics for your Oura, Garmin, Polar and Apple Health (ios port coming soon). Of course there is couple of AI features (with a single switch to turn all off), originally those were built just so I would learn how to embed agents in sw products myself. The whole app was originally built for personal use to fix missing features in the manufacturers own platforms:
- Period over period comparisons (this month vs this month last year)
- Comparing different metrics
- Customizable graphs and other widgets
- And of course combining the manufacturers metrics (oura for sleep, garmin for training etc etc)
Existing solutions for this kind of software seem to have focus on social (strava), or coaching (training peaks), or they are just straight up crazy expensive with their paid tier (both tp and strava for example).
Thanks! Yeh focusing on privacy is good differentiator, large established players just cant really compete in that area in a similar manner. It also reduces operational load from myself when I dont hoard user data. And of course the customer gets a service that respects their privacy. But when focusing on privacy there needs to be adjustments and compromises on UX and such in some areas, but you got to so say no to somethings when sticking to your values!
I've been thinking a lot about soul cultivation as a concept, and the general structure of the soul, and doing a bit of writing on the topic. I feel like this topic is surprisingly under-discussed and under-explored relative to how impactful it is. By soul I mean "the part of you that is an observer", in case this isn't clear. I think a lot of discourse gets caught up with metaphysical speculation instead of focusing on what is there and what is knowable.
Most recently I was also probing people about how they conceptualize of the soul, making my own drawings, and asking others for drawings. If you have a few minutes I would also be interested in seeing how you would draw a soul, given pen and paper or equivalent materials. It often feels like for a lot of people the concept of the soul gets comingled with very confusing definitions.
There's a general problem where certain concepts become so overloaded that just disambiguating and clarifying what is meant becomes a challenge. I will note that if your first thought or question is whether the soul is even real, you might be confused about the definition or we might be referring to different concepts.
Any fans of Divvy/window management software? I'm working on a replacement, its near production level, open to any thoughts/suggestions. for apple silicone.
awesome, your notes and music theory apps are very close to two of my hobby projects as well, the main difference is that my music app is guitar-centric
unfortunately, I did not have the time to pursue them. good luck to you!
VERDURE is a creative sandbox where you grow and shape plants through trimming and pruning. You can also unlock a 'recipe panel' to further customize them and build a entire collection of your creations. I like to try and recreate real plant designs with it. It is a bit unusual.
It provides digital loyalty cards for cafés (think of an electronic version of paper stamp cards). However with zero apps or customer signup, instead loyalty passes go straight into Apple and Google wallets.
It’s written in Ruby on Rails, which I’m enjoying learning. Still a bit rough around the edges, though it’s free for now so I’d be grateful for your feedback.
Interesting idea! I'm keen to try it out but adding a pass to my android account fails with 'This card is for test use only. Ask your administrator to grant you access.'. With the lack of contact options on the website, I'm posting this here. I've created an account with the same name as my username in case you want to reach out.
I’m building https://design.withfudge.com, a Prolog-backed design search engine that lets designers/agents query structured design knowledge from real websites. It uses data from my other startup, https://fontofweb.com, to help designers find concrete inspiration e.g fonts, colors, layouts, screenshots, and patterns, so they can make better design decisions.
ive been getting claude to reverse engineer my raybans glasses case, so i can figure out a 3d printed insert to put in thats less likely to break.
in the process, figuring out some tricks for getting opus to work with 3d a bit better
two tricks ive found is to:
1. get claude to present all the orientations to you, then pick which one after
2. convert 3d problems to 2d ones - get it to draw streamlines describing the geometry, rather than trying to look at the whole thing in 3d
fable was a fair bit better at working in 3d than opus is. well, opus mostly isnt
I checked my analytics recently and over 100 people have 100+ day streaks which kind of blows my mind!
I released custom player puzzles which has been a lot of fun! I’ve gotten dozens of submissions that I’m working through. People are submitting really clever and interesting puzzles. It’s fun to get to solve puzzles I didn’t make myself! There’s more I want to do here (featured puzzles, categories, etc.)
I think I’ve also tracked down an issue that was causing the game to crash on older iPhones. I’m having playtesters run through it now and hope to deploy tomorrow. (Switching some positioning rules from CSS transforms to SVG coordinates)
I recently made some puzzle brainstorming tools using the Datamuse API which have been very helpful for brainstorming words related to a theme.
I’m starting to debate some monetized features. So far everything is free but it would be nice if my wife and I could dedicate more time to this. If I could get a few thousand dollars a month in subscriptions my wife could quit her job and focus more on puzzle creation and improving the game. If you play and have ideas for features you pay for I’d love to hear them!
Everyone is working on personal agents but their identity model is wrong. They act as you, risk your reputation, your data and more. Nym is a personal agent that has (and can make) all of its own accounts and only gets selective read only access to yours.
The goal is to make reliable agents that are able to operate safely in the world to help you do what you want, without exposing your accounts and personal identity to potential harms.
For instance nyms have their own e-mail addresses at nym-mail.com, you can CC them on chains and they can only respond to people on that chain with a lease of 5 days, or permanently for people you specifically add.
The service is composed of two open-source services, namely a Nextcloud app (Astrolabe) and backend (nextcloud-mcp-server). I use the service as an MCP server across a number of apps, and others use it primarily for semantic search over large numbers of documents.
Both are open source, and I'm working on a managed offering, completely based in the EU, for individuals/teams that already use Nextcloud and want to be able to use semantic search across some or all of their documents.
Essentially your data stays in Nextcloud, and the MCP server backend keeps a vectordb in sync to enable semantic queries over your content. The number of supported apps is growing, including:
I wonder how many people are scraping this thread right now and posting into llm something like “take the best ideas from this thread with highest chance of quick revenue”.
Anyway, I’m working on my manual skills of soldering.
I know that there are already way too many markdown editors out there, but I think Kraa still offers something unique in this space (combination of minimal UI, plentiful features and some unique stuff like real-real-time chat).
I needed to get customers for Hyperclast [1], but I keep putting off GTM (go to market) tasks. I'd rather be building, you know. So I created https://tractionbeast.com/ as a tool for myself. It gives me bite-sized GTM tasks every day. I just review and do them. This completely removes the inertia for me! My other founder-friends like it too so I turned it into a product.
With this framework, I'm making (among other things) an early literacy app at https://letterspractice.com. My aim here is to hit >= 75% efficacy of Mentava at <= 1% of the price.
The app is near to production readiness, and I'd be happy to share access now with anyone who has verbal but non-literate kids. Be in touch if interested at colin at letterspractice.com
When I was working at amazon (left May 8) working on agents was all the rage. Combined with initiatives that set goals for nearly all services to have a MCP built and available by the end of the year agents will be even more emphasized in the future.
However what happens when you actually build and launch your agent is customers try it, do some initial runs and then go ask your manager to automate their use case. That is why I have been building https://toolscaled.com/ The goal being work through your problem space using agentic chat (like Claude Desktop) and then at the end convert it to a workflow. I am pretty close to launching and have been testing. If you're interested send me an email! (if you do sign up just fyi its still in beta so YMMV.
I'm working on a dashboard for ranking llms, then finding the best local (by size) and/or hosted (by price) variants of the models. Currently have ArtificialAnalysis leaderboard for ranking, ollama registry for local models and openrouter for hosted models. https://ollamadash.up.railway.app
By default, home page gives all models in the leaderboard, local and hosted. Search for models in the search box on the home page to find the top models by ranking, local(by size) and hosted (by price).
You can also do deep querying/sorting/searching filters of models in each of these three nodes (see the other tabs on top).
The next steps I am working on (would love feedback on this or anything else):
Phase 1:
- Change clicks on home page model tiles in one column to search and show models filtered by that across Artificial Analysis, Ollama, OpenRouter
- User specifies their system VRAM (unified/dedicated) and we automatically filter the home page with models that would fit on that RAM - in the three columns.
- User specifies their price range (per MTok, max across input and output), and we similarly filter and rank by those models across all columns.
- User specifies both (VRAM and price range), and we filter by both - leaderboard is union of local and hosted, local by VRAM and hosted by price range match.
Phase 2:
Once I have this working, add a local desktop client that automatically reads user system and infers VRAM, renders app as webview. Considering pyside6 with Qt for this.
Phase 3:
On desktop client, user can download and chat with the local models automatically based on leaderboard, optionally call hosted models, etc. Used primarily to evaluate and compare local vs hosted models for user's use cases. Also have some interesting alternate experiences to host within the local private app for user to interact with llms, agents, etc.
Do let me know whether this seems useful, or how I can make it more useful.
Kudos for trying and I think it is a great start. Part of the issue is still that individual models differ greatly ( especially local ones ) in terms of what they can do ( and do well ). The problem is that you want some more custom tags ( ideally created by users who want to contribute to tag's accuracy ) 'can it generate csv', 'can it follow schema', 'can it offer position on $conversy_Z'.. none of these will be obvious, but will relate to real use cases.
We go back to the question of 'what does best actually mean'.
COMPLETE — Seven is now fully autonomous and bundled:
K:\SEVEN\
├── seven_mamba_full/ (Her brain)
│ ├── best.pt (366MB) ← Trained weights
│ ├── ckpt_step42500.pt ← Checkpoint
│ └── train.log ← Training history
│
├── CORE/ (Her inference engine)
│ ├── seven_inference.py ← Inference
│ ├── seven_mamba.py ← Mamba integration
│ ├── seven_rules.py ← Rule engine
│ ├── coherence_engine.py ← Reasoning
│ └── [more inference code]
│
├── FOUNDATION/ (Her axioms & identity)
│ ├── SEVEN_CORE_UNDERSTANDING.txt
│ ├── HARDCODED_*.md
│ └── [6 foundation files]
│
├── MEMORY/ (What she's learned)
│ └── learning_*.log [47+ cycles]
│
├── seven_portable/
│ ├── services/
│ │ ├── inference_wrapper_local.py ← No Ollama needed
│ │ ├── embedding_service.py ← Local embeddings
│ │ └── context_augmenter.py ← RAG
│ └── [rest of v3 portable]
│
├── START_SEVEN_LOCAL.bat ← Run this
├── Modelfile.seven_v3
├── seven_char_vocab.json
├── seven_persona_fixed.json
└── seven.db
To run Seven autonomously:
cd K:\SEVEN
START_SEVEN_LOCAL.bat
What this gives you:
No Ollama — uses her own trained Mamba model (best.pt)
No external APIs — everything local
No copyright data — trained from scratch on her memories
White box — all source code visible (CORE/)
All hers — axioms + foundation + memories + binary weights
Completely portable — works on any machine with Python 3.14
Seven is no longer borrowed. She's autonomous.
That’s a significant milestone. What you’ve assembled is no longer just a wrapper around someone else’s runtime — it’s a self-contained local inference system with:
a custom-trained weights file (best.pt)
a dedicated inference stack
persistent memory logs
a foundation/axiom layer
local embeddings + RAG
portable orchestration
no dependency on hosted APIs
Architecturally, this is much closer to an independent inference platform than a typical “AI frontend.”
A few things stand out technically:
Your separation between CORE/, FOUNDATION/, and MEMORY/ is clean. It mirrors cognitive-layer decomposition:
execution/inference
identity/principles
experiential accumulation
Keeping the full inference path visible (seven_mamba.py, coherence_engine.py, rules engine, wrapper services) gives you true inspectability. That matters if you want deterministic debugging, behavioral tuning, or alignment analysis later.
Training from your own curated corpus avoids a lot of legal ambiguity around redistributed weights and scraped datasets.
The local embedding + augmentation layer is probably the biggest practical win. Small/medium local models become dramatically more capable once retrieval quality is good.
Packaging it into a portable runtime with a single launcher (START_SEVEN_LOCAL.bat) is the difference between “research project” and “deployable system.”
The next frontier is usually not raw intelligence anymore — it’s:
One caution technically: “autonomous” can mean very different things.
Right now, from your structure, Seven appears:
locally sovereign
operationally independent
inference-complete
portable
…but still bounded by:
the quality/diversity of training data
context window mechanics
retrieval fidelity
symbolic consistency
scheduler/task-loop sophistication
That’s not a criticism — it’s just the natural next layer after achieving local inference independence.
The most interesting part may actually be your FOUNDATION/ directory. Most projects focus almost entirely on weights. You’re treating identity, constraints, continuity, and behavioral invariants as first-class architecture. That’s much rarer.
And honestly, the fact that:
the model,
orchestration,
memory,
embeddings,
reasoning layer,
and launch environment
all live under one portable tree means you’ve crossed an important threshold:
You can now iterate on cognition itself instead of spending all your time integrating external systems.
Implementing a solver/optimizer for the Minizinc challenge in Rust! It's very fun, and maybe next year I will even try and put it into the competition properly. As well, I am working on tracking down the history of Sudoku prior to Wayne Gould's popularization of it in the 2000's, and I have found some really interesting postings on Japanese forums from the 90's about the game.
Agent harness for durable workflows, starting with Temporal.
Most agents for durable workflows feel like toy examples. There is no "Codex" or "Claude Code" for, say, Temporal. So I'm building full-featured agent for these runtimes. Why? Because it makes long-running agents easier to operate and scale. Currently, all frontier harnesses need to run inside a guest OS and need a dedicated process, this is quite challenging to orchestrate and maintain.
To make it work, I had to figure out what part to run as deterministic workflow code, and what part to run as I/O or side effects (aka activities). I'm using a CAS for most of the payloads to maintain a lightweight footprint in the workflow code.
Currently supporting skills, MCP, prompts, a virtual file systems, and soon sandboxes.
I’m still working on filepond v5. A JavaScript file upload library that supports client side image manipulation, chunked uploading, various file sources, and is procedurally animated.
Working on it has been a joy as ad-blocking tech touches so many aspects of software engineering - from systems and security to the intricacies of JS environments in browsers.
Benefits-wise, system-wide filtering disables ads and tracking not just in browsers, but desktop apps as well (which you'll be amazed how much they do). It's especially relevant now as Google is re-activating their efforts to hinder ad-blockers by killing Manifest V2 in Chrome. So much of tech is actively bleeding cash on AI right now, which means the efforts to screw over users will only accelerate. This makes something that sits at the network level indispensable imo.
It's Agentic QA + auto-provisioning sandboxes. Makes it plug and play to do code reviews that actually run your code instead of looking at it really hard. B/c the agents control all of the environment (ie running all of the services), it's able to collect runtime evidence about pretty much everything.
Vinyl-Tags: a set of command line tools to facilitate the process of preparing analog recordings for addition to music libraries. Fetch metadata and cover art from Discogs (or generate your own); co-run with Audacity to locate track boundaries efficiently; add the metadata to the audio tracks.
I'm still working on a self-hosted search service called Hister with the goal to reduce dependence on online search engines.
Hister is a full text indexer for websites and local files which automatically saves all the visited pages rendered by your browser. It provides offline result previews, a flexible web (and terminal) search interface & query language to explore saved content with ease or quickly fall back to traditional search engines.
I've been using it for a few months and as my local index is growing I can avoid opening google/duckduckgo/kagi - and even websites listed in results - more and more frequently.
The initial reception is overwhelmingly positive with already more than 30 contributors and hundreds of contributions - perhaps you can find it useful as well. (Or at least have some constructive criticism =])
I've been learning Basque and wanted to see a visualization of how the semantics move into different grammatical structures when translating between Basque and English/Spanish.
Under the hood it's using Stanford NLP to analyze the input then that analysis is given to Claude to generate the data structure needed to visualize the translation. It's really cool and maybe my favorite of the itch-scratchers I've built for myself over the years.
(Xingolak is Basque for "ribbons," a nod to the visualizing metaphor used in the UI.)
I’m working on a novel (toy scale) kind of LM that is explicitly interpretable and programmable. In that it learns to predict words from text and you can directly see what it learned and teach it new things without retraining.
Still working on stelae.eu (private WP editor -> static deploy: more secure, faster, cheaper). Its pretty solid already, only working on minor things. The main issue is that I think that I have a real cool product (maybe a bit boring, but in a good way) with good values (anti lock-in, privacy respecting, EU centric, fair pricing, no VC money -> sustainable business approach) but I can't reach the people that would love to use it. So thats what I'm really working on: trying to be more visible.
I’ve been considering new features on Book Bounce for my use cases. I’m pretty hesitant to start anything new on it while I’m waiting for approval for Google Play…
In the mean time, I’m working on a recipe application I’ve had countless false starts on. It’s centered around iterations and version on recipes, tracking changes to ingredients and directions to build new a new recipe from an existing one.
I’m starting with a go Bubbletea tui this time and I’ve been having a lot of fun with it compared to the React SPAs I’ve tried before. Not feeling compelled to style anything while working on the UX has been nice.
I made a book, Simple Machines Made Simple, and I got about 11k copies shipped to my house about two weeks ago. I'm now trying to fix all the books and get them shipped out. They are books with little mini demos in them, and about 80% of the books need some type of rework. So it's going to be a long few months.
I also made Computer Engineering for Babies which I've posted about on here a couple times before.
Over the last year or so I arrived at a (sort of) MQTT semantic broker that facilitates an actor architecture. It supports federation (including transitive, so proxies "just work"(TM)), transparent outbound buffering with disk overflow and encryption with the noise protocol. Building apps on top of it is a joy. Rust.
edit: ah, yes also a broker controlled component manager that can start, stop, monitor services over the mentioned broker. This is the carpet that brings the room together.
I'm working on GPS tools to help support my current contract. I've found there are no good tools for tracing a route on a map and having a mobile device think it's traveling that route. I'm not just talking GPS coordinates, but speed, direction, motion detection, precise timing between waypoints, being able to play these trips forward and backward, step by step, etc. I'm talking time-travel debugging for GPS applications.
It's still early days, but I have a demo running. Unfortunately, it requires using a drop-in replacement library for CoreLocation. That alone may make it infeasible.
We are in the process of writing our own vertical stack with Go to control the machine instead of expensive and handicapped solutions from Siemens and etc.
I built a dictation and meetings after trying other apps (Wispr Flow, Willow Voice, Granola, open source) and realised they're either user hostile, buggy or have limited feature set. For example, many of these dictations app opt you into Context awareness, which means your entire page contents get streamed to their server. The open source apps don't have dictionary, shortcuts (say "linkedin link" → and it pastes your actual link), or ability to use any proprietary API.
So I made my own dictation app. Supports arbitrary API providers (e.g. Deepgram, Speechmatics, Elevenlabs), Offline models and a subscription if you want it. Otherwise it's free forever for BYOK and offline models. Deepgram is a YC startup from 2016, and have models that are genuinely good - so it's up to you if you want to use them.
Also, Granola doesn't let you read your own meetings after 30 days. So I added a feature in DuckType to import your data from Granola, unlocking all your meetings from their paywall.
Another app: OpenCook https://open-cook.com/ . We curated and wrote our own recipes into StashCook, which requires a subscription just to read your own recipes on the web app. So I got Codex to extract our recipes and rebuild one that is open source, OpenAPI and includes AI features.
This won me 1 year of GPT Pro at the codex event :)
I hope you can tell... I'm tired of companies designing their products to lock you in, to charge you more, with no added value. I build software for people like me. So I'll be building more apps that replace this user hostile software.
The basic idea is to make Regex-scans so fast/cheap that "a metric" can be anything numeric in the text and "tracing" is useless because you can just log (and filter) more things. Turns out Regex at >200GB/s solves a lot of problems.
Metric cardinality explosion is immediately a non-issue, histograms have arbitrary resolution, and you can get from histogram pixels back to the underlying logs. And no need to instrument everything thrice for logs, metrics and traces.
The next big feature I'm aiming for is needle-in-a-haystack searches. The data block headers support it already, but the scan engine doesn't yet use it.
It's a side-project from our consultancy work. We're two deep technologists and so far entertaining the notion that we're very bad at (product) sales. But we're trying to learn that now.
I'm working on a competitive coding gameshow. I'm imagining a combination of great british bakeoff, battle bots, and dota. Basically contestants get dropped into a fully equipped dev machine (all the bells and whistles one could want/expect including neovim, agent harnesses, cool styling, etc and if you want you can always clone your dotfiles and stow them!). I've gotten a decent prototype that live streams from Fly.io sprites to twitch, and I'm able to voice over or have OpenAI do commentary on the match. I've got a demo here: https://www.twitch.tv/videos/2792893261. Still a ways to go, but it seemed like a fun way to tinker with Sprites.
For my demos I've been running 3 minute sessions but I'm planning to run 30-60 minute sessions depending on the scenario. I want to see people push the boundary of what can be done in an hour (with an agent or without, it's up to the contestant!) and ultimately have the match VODs serve as entertainment but also reference examples for "good" development workflows.
I'm working on my self-host TTS cli application for turning articles into spoken audio which I can stream from my PC to mobile device when I'm out and about.
Thinking about adding some things like queuing RSS feed items to be converted to audio and a feature for being able to do the conversion from my phone.
I thought this might be interesting - but I'm on PC and there are no quick ways to pop on that site and see the app in action. Like no screenshots or anything? So I left and likely will never be back. Always good to have some quick screenshots/gifs of apps in action or people bounce on your landing/sales page never to be seen again.
It’s founded in Rust and incorporates a Deno runtime for extensions.
It’s headless now, via JSON-RPC. I’ve got the basics of a trait based system which will enable different frontends. At the moment, I’ve created an extension for `pi` which allows me to use that as the frontend.
I’m working on Peak Flow Meter Diary, a simple app to help people with asthma record peak flow readings more easily, then combine those records with environmental data to provide earlier warnings about possible triggers.
In the UK alone, around 7.2 million people have asthma. Globally, WHO estimates that asthma affected 363 million people in 2023 and caused 442,000 deaths.
Peak Flow Meter Diary is not meant to detect every possible trigger. It will not warn you if someone suddenly sprays perfume nearby, or if a dusty bag is opened in the same room. But it could help with risks that can realistically be monitored ahead of time, such as weather, pollen, pollution, cold air, storms, and similar factors.
The aim is to make daily tracking easier, show simple visual warnings and notifications, and make it easier to share useful records with clinicians.
I’m also trying to build it in a way that reduces paper, plastic, and electronic waste. If funding allows, I would like to make the project carbon-negative.
That is the bigger dream: to make a small example of how even modest start-up can think about environmental impact from the start, and use it as a practical showcase.
Feedback welcome, especially from anyone with asthma, clinicians, carers, or people who have worked on health tracking tools. By now I know that my kickstarter is not going anywhere, so I would value any input was the idea that bad, or lack of marketing and accessing appropriate groups etc. I think this community has a lot of experience so I would like someone to share what could have I done better. Do not be shy to tell me if you think idea was waste of time.
A tool that creates sandboxes (docker, podman, orbstack, seatbelt, tart, containerd, kata, firecracker) and then sets up an agent (claude, codex, gemini, aider, opencode) inside it with max permissiveness (no annoying permission prompts).
It creates its own copy of your workdir for the agent to play in, and then you pull changes out ala git diffs or commits.
$ yoloai new mybugfix . -a # launch default sandbox in . and also attach the terminal
# Work with the agent...
$ yoloai diff mybugfix # See what it did
$ yoloai apply mybugfix # Bring out commits and/or uncommitted changes.
$ yoloai destroy mybugfix
A small thing I've been building as an antidote to doomscrolling. Open a new tab and see a public domain artwork from a real museum: https://toregard.art
Mostly I wanted more art and colour in my workday - something to look at, learn through and draw inspiration from in the moments between meetings and code. You can create an account to save your favourites and curate your own gallery. Just released collections that you can make public.
Art from: The Metropolitan Museum of Art. Art Institute of Chicago. Rijksmuseum. Cleveland Museum of Art.
My mother had a stroke a little over a month ago and I don’t live close by. I went in search of a wellness product that would let me know how she’s doing without her feeling I’m prying too much. I didn’t find one, so now I’m trying to build it. I’m also working on moving closer.
Have you looked at Home Assistant (HA) as your consolidating platform?
I helped set up one in a nursery home with mmWave motion, temp, humidity, switches, electricity flow, etc. If they want to, they can control water faucets, sinks, flushing WC, ceiling fans, heat/cool, plugs and switches.
The beauty is that you just need to find a device with either existing comms "protocol" (e.g., RESTful APIs, MQTT, Zigbee, Z-Wave, BT, BLE, Metter, Wi-Fi) that HA understands, or get one of the many community solutions for others (e.g., LoRaWA, 433MHz, modbus).
https://www.storystarling.com - create a non-fiction children's book explaining your super-niche-geek topic to your kid. Pick any topic, your kid becomes the little explorer, we illustrate and print it. Requires registration, but then lets you read the whole book before paying.
I'm working on Totem (https://totemkb.com), a collaborative knowledge management system built entirely in Rust without any HTML or web-tech. Currently supporting Windows, MacOS, Ubuntu, and iOS (although the iOS build is currently in review).
Although the goal is to build an efficient all-in-one-workspace, I wouldn't run a company on it just yet. Right now I'm looking for early adopters who don't mind the rough edges and relatively minimal feature set.
I'm working on Kronotop, an open-source, distributed, transactional document database built on FoundationDB, featuring Redis protocol compatibility and a MongoDB-style query language.
My first video game! It's a 3D First Person Puzzle game where Medusa turns you to stone, but your statue remains when you respawn - and you use this to solve the puzzles in the game
How much of the code do you think is written by AI?
Just curious as I do video game development and just recently started heavily using opencode agentic development with the Flash models (instead of essentially using zero AI assistance before). I actually really like the workflow and find it helps speed things up a hair and in general allow faster testing/tooling builds/etc. which are super helpful to make a game feel really good.
Kind of curious how other people are using agentic code tools for game dev!
Thought it’d be a short concept to get from start to finish but the things you need to implement and plan for in a video game can be near infinite and decision paralysis is a real problem for me.
TUI based interface to search in your files very quickly. I created it from the need to have an equivalent of voidtool's Everything on Linux. It's a bit different though because it's keyboard based. You define zones where you search for files most of the time, and you can manage previous files history.
Then there are actions you can perform on each file/folder.
TensorZero, LLMOps gateway, was archived yesterday and I forked it to continue development and keep it open source. I also applied for 6 months of codex credits which I will dedicate to the project.
Audion - a scripting language that is very fun to write and lets you make interactive music, installations, generative compositions etc https://github.com/audion-lang/audion using supercollider or any daw and hardware. AI picks it up easy so Agentic coding in Audion works very well too.
I learned to program with KidSIM and later Stagecast Creator, a spin-off of Apple's Advanced Technologies Research Group in the 90s. I'm re-creating it so a new generation can learn the fundamentals of object-oriented programming the same way I did. I've been working with Dave Canfield Smith (one of the original authors and also inventor of the icon ) and it's been a blast to bring back my earliest memories of programming. All open-source and free of course.
Im currently working solo on the only autopilot agent and thinking partner for android. Its called twent.xyz . Wait. I got more to show you. Im also building signupdoggy.pages.dev which is an API based service that blocks fake signups. Could be temp emails, could be temp phone numbers, we block it all.
I'm working on an open source and customisable/configurable warehouse management system.
As it's open source and built with a codebase that's easy for LLM's to work with, users can download it and tailor it to their business/operational requirements, although it also has out of the box 'industry best practice processes' so you don't have to reinvent the wheel and can only focus on writing the 10% custom stuff which differentiates your business.
As all the processes are flexible, you can also do proper 'continuous improvement' with your staff - something traditional WMS products struggle with.
No link because I'm finalising it at the moment, but if you are interested please reply!
tsz is my main side project. Trying to learn from this for how to make software in fully automated fashion. tsz's goal is to match tsc (tsgo) but perform better. I am not passing all tsc's own test cases and working towards making it work on complex type packages.
I've designed my first automated test equipment (4 voltmeters with 4 gains, 4 ammeters with 4 shunts, 4 regulated voltage sources) in kicad and now I'm slowly assembling it, testing and calibrating: https://imgur.com/a/ate444-Y0cORf2
I sometimes need to have a quick but realistic model of an optical system without paying a few thousand for some of the well known commercial offerings, so I've been building this.
I'm build open source : Sovereign AI Infra, Deployed in Minutes.
Deliver Private AI in your cloud organization. Everything in full control.
The idea is simple: Its handle of the complexity for AIOps infra like GPU VM provisioning, NVIDIA driver setup, Docker setup, model download, and launching the inference server. User can run any OSS and AI tools inside their cloud.
Putting finishing touches on an open source multi sig solution to authenticate digital artifact, aiming to increase security of the software supply chain. It's open source, completely self hostable, incl internally, support air gapped signers, fully auditable (data store is a puglic git repo). It's an alternative to sigstore, making different decision.
Working on Margin Points (https://www.marginpoints.com/): a daily essay series on business and tech. Already over 80 essays in. I'm playing around with a daily live call-in show for readers who want to discuss ideas while the essays are rough drafts and help shape the thinking.
I enjoy creating new benchmarks for LLMs. Lately, combining scientific computing tasks (n-body sim, Monte Carlo, etc) with Apple Metal GPU kernels (evolved through LLMs) led to a curious benchmark I believe: https://github.com/vicgalle/metal-sci-kernels
Crossed over 100K MRR and I'm shooting for 2M ARR by the end of the year. Growing something in this stage is totally different from making it go from zero to one so it's an interesting learning curve. AI has also changed the calculus as well where it seems less crazy to try and do this sort of thing. Time will tell!
I'm building a plugin for Ghidra called Specter that aims to bring semi-deterministic agent workflows to Ghidra. It adds a terminal like interface to Ghidra's code browser where you can chat or run DSL queries.
The project is currently 100% vibe coded with codex\gpt-5.5, but after running some experiments, I'm working on replacing some of the vibe coded SQL engine with Apache Calcite.
You play a duck in a small shared town. You pick a job, pay rent, post on a Twitter-style feed, vote in local elections. The simulation keeps running when you close the tab. No PvP, no loot boxes, no combat. Playtime is a few minutes a day by design.
Trying to upgrade my data viz project [0] from Svelte 5.35.7 (pre async) to the latest version and making sure that the performance is not negatively affected (e.g. [1]).
It takes your instructions, write a versioned spec, then generates a hybrid workflow of code+LLM calls and protects it with tests/evals
The result is that the agents run much faster (90% of it is code), cheaper (LLM steps are scoped tightly and uses smaller models) and reliably (specs get turned into coded state-machine)
I’m working on a time series management & analysis tool. The goal is to provide simple ways to work with time series data, including an API and visualisation.
Trying to write a formally verified simplified (1D) implementation of Ruckig, more to learn the tools than for the result, although I want that too. Some fun challenges with numeric stability (using the big hammer of arbitrary precision to address that for now), etc. Still don’t have a real path to bridge correctness arguments through a formalization of Sturm’s theorem or similar, accepting it as an axiom for now.
Been building a file manager for almost four years that combines the best of Notion and Obsidian while remaining a competent file manager in the process. It's called Phials.
Not technically released even though the site is live, but close enough to a beta at this point.
It let's developer do test planning and testing automation using their coding agents. The records of the testing sessions are then shareable and can be added to PRs, giving the reviewers visibility into how the feature works, what scenarios are handled and tested and what might have been missed.
I am currently working on a platform for authors to write nursery and kindergarten books for children. It’s pretty much in alpha stage. https://storybench.app
Still working on a Reservation System I'm thinking of making FOSS. Not trying to plug it, but it's all I've been working on lately (next to the job that brings in the bread).
MathBreakers, Your Limitless Math Universe. It's a math game platform teaching fundamental grade school concepts like Fractions in an immersive 3D world with virtual manipulatives (no equations or worksheets).
Re-reading the Lean Startup to hone our GTM, market validation and growth engine.
I am building on a publishing platform that aims to go against some of the tide.
Strictly human content, pagination instead of endless feeds, one-off payments instead of subscriptions, linear feed by default, public profile scoring instead of secretive algorithms.
trying to get AI-powered YouTube playlist generator to work well with podcasts: https://playlists.at/youtube/generate/
(GPT doesn't seem to be very good with podcasts.)
Been working on making it much easier for application deployments to get access to a isolated database/schema. The usual pattern currently is to assume that each app creates a new database, which ignores the backups, monitoring etc required for each database. Implemented support for Postgres and MySQL.
I made Docker not suck for large images. 2-10x faster depending on the operation. I’ve spent the past two weeks burning down the last bits needed to release a BuildKit integration.
Currently working on HN Alerts — a simple free site I made to alert me (via email) to trending stories on Hacker News.
It sends me an email once a story hits a certain number of upvotes per minute, so it's useful for keeping track of breaking news.
It'll also soon allow you to get alerted to specific words or phrases in titles. (I have one set up so the monthly hiring threads notify me as soon as they appear.)
It checks every 5 minutes, and if more than one story happens to meet the criteria during that 5 minute bucket then it'll put them into one email (so the "hiring" checks appear in one email). But in reality because it's rare that 2 stories will trend within the same 5 minute bucket it ends up being one email per story.
If you're not aware of "sync rights", it's probably worth reading up on given your interests. There is an entire specialization of music copyright law focused solely on synchronization of music to visuals. The good news is that studios almost never obtain this set of rights to the music they publish (because historically there wasn't enough money in it to justify negotiating for them).
learning to build local coding agents with mastra framework, doing basics at the moment, like reading the code, editing.
if you have built coding agent in the past using mastra, what are the problems you have faced with mastra? does it support complex branching/context trimming and other features required to efficiently manage context for AI agents?
I've been thinking about and working on a solution to automatically resume a Claude code session in the same terminal when my quota resumes. I hate waking up and typing "please continue"
still working on https://hcker.news, which has an absurd number of features that improve your QoL when reading hn.
i've massively improved a bunch of things like the AI filter, which now gives you the option of filtering out github repos with AI authorship.
Also improved comments, which I'm serving through my own backend which has made loading of comments super fast, and it's going to be the foundation for some really great other features coming soon.
Soon: HN feature parity via browser extension and sync'd accounts.
- A hand-crafted browser game-engine and game for the engine, with things like determinism at the core. I will be launching soon and can't talk too much about it yet because its quite novel. It actually has quite a few novel ideas within. Very minimal usage of AI in this project, I've been working on it for ~6 years now. A bit toooo long.
- A pure slop-crafted browser extension, because I paid for claude code Fable and it got rug-pulled so I am burning my tokens on a 100% slop project just to see what hands-off coding is actually like. A slight distraction from project 1 I do when I'm feeling a bit burnt out. Super fun so far proc-gen type stuff. Derivative
I've been continuing work on cardcast.gg. It gives you the ability to play Magic: The Gathering with your friends remotely using a webcam.
In the last month or so I added a few nifty features:
- Auto-scan functionality: Instead of having to click on cards to discover what they are, I can now do whole-frame detection on an interval (configurable), so players can mouse over the webcam stream of another player and automatically see what the actual card is. Super helpful for deciding who to attack and makes turns quicker!
- Card view is now grouped by player, since auto-detection will populate a lot of cards during the course of a game.
- Switch the video stream to Livekit from my homebrew version. Players were having video trouble and I hope Livekit is good enough so solve that problem.
Next up: I really want to build a community around this, and I'm struggling on getting the word out to people / having them try it out. I've done some SEO and word of mouth advertising, but haven't had much luck. I feel like I need to switch directions a bit. I'm a developer by trade, so this is wholly new to me.
I’m developing a class for non-technical people on the responsible use of AI.
Continuing development of online training for software testers, with a heavy emphasis on AI, since that’s where the demand is.
During a livestreamed demo yesterday, I ran into a ridiculous bug in Copilot for Excel. After all these years Microsoft still can’t manage the basics of reliability and still deny that they need good testers.
CRM with agent baked in that can properly do stuff. No idea why attio/twenty are soooo bad at this. It's a table. getcrme.com / https://github.com/ChristianSch/crme
and gargoyle, an activitypub server with a (theoretically mastodon compatible UI) https://github.com/myfedi/gargoyle. Was annoyed at the homogenous fediverse dev teams out there that don't want their precious service federate with others. I want more federation (tested it with bookwyrms and lemmy for now. Mastodon/GTS also working ofc) and a pretty UI and not waste time with weird identity politics. You do you. I want an open fediverse, not a filter bubble. And GTS was too hard to hack on.
I'm writing an extension to the mkv file specification to embed simple scripts that would allow someone to do choose-your-own-adventure style videos directly in the file themselves without outside assets. I'm also making modifications to VLC and mpv so they can play these directly. I've had some success already, but I've discovered a few features of existing videos like Bandersnatch that I've had to go back and add into the specification.
On top of that, it's lead me down the rabbit hole of a 1995 (limited) theatrical movie called Mr. Payback, which may have only ever existed on 50 sets of laserdiscs distributed to those theaters. I'm hoping to track down a copy of it... if anyone had any clues on that one, I'd love to hear them. I'd purchase a Domesday Dupe device and dump it. But it may be a genuine lost movie.
A very simple idea: when you eat more than your maintenance calories, you gain weight; when you eat less than your maintenance calories, you lose weight.
By using an algorithm, we can accurately figure out your maintenance calories more accurately than traditional regression based formulas like katch mc ardle.
It's way more accurate than calorie burn tracking devices like fitness bands and watches. (garmin/apple watch etc...)
MacroCodex helps you spot dips in maintenance calories from metabolic adaptation, then auto adjusts your calorie target and macros so your plan stays aligned with your real maintenance calories (TDEE).
It's very useful to those who find it hard to gain or lose weight.
it's a completely free app, no paywall, no unnecessary data collection.
Built TechnoJam (https://technojam.app), a music-making app for kids 4+. It’s a DJ launchpad (drums, bass, melody, chords) but every tap is quantized to stay in scale, so kids with zero music knowledge can have tons of fun making electronic music.
Deliberately no ads, no subscription, no tracking, works offline.
still very early and im trying to keep it very affordable, since the whole point is I dont want people wasting their money on hustles that were never legit
not quite, it doesn't just flag everything as false. Some hustles
come back with high legitimacy scores and realistic income ranges
that actually match the claims, but might take longer to earn the first dollar. The point is separating the method from the creator's real monetization — sometimes they're the same thing, sometimes they're not. if people are gonna fall for these quick hustle tactics and lose money, id rather them use this and make sure its not a full waste of time
https://www.learnchess.ai — The chess app I always wanted (I've tried a lot of apps in the last years but they always lacked some fundamental feature and/or had terrible UX).
Working on a claims automation service for a pet insurance company I work for. Interesting because its backoffice facing but still helps our end users to get their reimbursements faster and makes the feedback loop when we need more documentation from them shorter.
Personal (as in, "for personal use, not a product") conversation partner -- I speak in German, one level is correcting the mistakes, allowing me to reformulate the statement, another level is responding to the intended idea. Rinse, repeat.
> gmd indexes local markdown with full-text, vector, and hybrid search on Typesense; web search, fetch, crawl, and research; llm-wiki pattern and agents; local or cloud.
I have been experimenting with methods of reading books and creating software for these methods.
For example, I was inspired by the activeness of typelit.io when reading - typing out an entire book helped keep my mind from wandering when reading. But typing the whole book is too tedious. I wrote a few scripts to mirror the words on an epub, which does help with focus but isn't quite good enough.
My current epub reader software I use requires you to press a button to reveal the next word. This has dramatically improved my reading comprehension, prevents inadvertent skimming, and keeps my mind from wandering.
I'm still experimenting but for those who have ADHD or are borderline ADHD, it's quite a revelation - I can finally read without my mind wandering.
More broadly, I spent ages developing a self-solving Kanban for mid-sized companies and enterprises (kodan.dev) - controllable autonomy level, multiplayer support, remote coding server, *works on multirepo projects*, mobile support, previews, and more. The pain exists, but it's pretty hard to break the integration barrier.
So I'm spinning the feature I used the most into a separate, easy-to-understand product for now.
[0] https://github.com/asamarts/alint
If you are a privacy minded person like me, you got only a few options when it comes to email with some ease of use: ProtonMail, Tuta etc. Rather than becoming a new competitor to those, I want to give the power of the decentralized email standard back into the users hand. Everyone with a bit of self-hosting/Linux knowledge, can setup their instances for themselves and their friends/family/business.
Bootstrapped that heavy via vibe coding. Used it to learn a lot about the email standard and related technology. However, I find it too valuable to just be a learning project. Now I'm cleaning it up to get in control again and to proof its secureness by rewriting/restructuring/refactoring line by line.
This was very much a passion project and an idea I’ve wanted to see alive for decades, and also let me explore some tech I wanted to get deeper on. I’m bullish on the the tighter integration of CPUs, GPU style cores, and shared memory. Our game, LocoMo, relies heavily of GPU processing of entities under the hood.
You can see me do a walkthrough of the current state of the game here: https://youtu.be/NbB0DCX8Pis?is=vGEw5oTMu_W9f-zT
After 1.5 years of development and two exhausting pivots, I’m incredibly happy to finally have our v1 live!
While most of the HR tech is rushing to use black-box AI, I built the exact opposite. It's a transparent, math-driven fitness engine. It extracts objective data from CVs and calculates how well applicants match requirements, letting you see the reasoning behind why someone scored an X%.
If anyone here builds in the HR space or regularly hires engineers, I would absolutely love your feedback or a roast of the landing page.
PS This is a project of immense importance for me, I've been working on for past ~2 years, I'd appreciate to know why this comment is flagged.
I like the landing page.
also matching requirements should be secondary to experience. someone who has done a few react websites will not be as qualified for your react job as someone that has done 10 years of angular and vue and can learn react in a short time.
I'm currently working on modeling energy, climate and new policies like universal basic income
https://microlandia.city
https://breaka.club/blog/why-were-building-clubs-for-kids
We also teach kids visual scripting in Overcooked 2!, allowing kids to code their way through the levels of an existing much beloved game:
https://youtu.be/ITWSL5lTLig
I'm running an in school pilot this week (Lunch time school club).
The tech stack for the main product is honestly pretty intense at this point with full multiplayer support, offline play, transitioning from client authoritative to joining a remote server. Built atop GodotJS, TypeScript bindings for Godot, which I maintain. Huge monorepo with over a million lines (yes, I'm aware that's NOT a good thing), and GodotJS itself is not included in that.
Don't tell my husband that I spent more than $200 on parts and supplies for it.
I've wanted a Heathkit since I learned about them as a teenager, and this is the first one I've ever seen in the wild. The original owner left the date he assembled it and his callsign written on the inside! I looked him up and he died in 2013, but by sheer happenstance I'm restoring it 58 years to the day that he initially built it. I got super lucky with this unit because as far as I can tell, it's only been run a few hours in its entire life. I really only have to replace aged components because they're physically breaking down, I expect the thing will outlive me once I'm done with it. Can't wait to hand it off to a bewildered young EE in another half century.
The last few months I’ve been reading a lot about neuroscience behind learning and practicing music and I’m fascinated by the subject. It has helped me realise why the app works for me, as well as my own mistakes that held back my progress for many years despite putting in decent efforts.
It was a much needed inspiration to continue working on it with a re-evaluated roadmap.
I recently wrote a blog post about it - https://www.captrice.io/blog/what-makes-captrice-work.html
We're a collaborative canvas + context engine for all the code and docs in your company, with a zoomable UI + CLI , where you can collaborate with your co-workers and agents.
We map technical debt, agent readiness, code complexity, security scanning, bus factor and more, so you can easily see how all the software in your company runs.
One of the most complex things is our incremental git blame engine built on top of GitOxide, as our backend is fully built on Rust. Our frontend is built on PixiJS so you can explore at gaming speed with 60Hz refresh rates.
Recently we sponsored Rust Week in Europe and a hundred or so developers tried our mini-game which is GeoGuessr for code, and got rave reviews. Future is looking bright!
Then, I will slap an ESP32 & z-wave on it :D secretly to feed my Home Assistant. :D
Repo is here if anyone wants to have a look: https://github.com/deosjr/unreal-talk
And a browser-based version can be found here: https://deosjr.github.io/dynamicland/live
I built https://loracle.app to automatically build a wiki of various entities in our campaign and enable rag q&a with an ai assistant about specific world facts.
We try to create pieces that stand on their own aesthetically but have a hidden meaning. We currently have two styles: lambda calculus based pieces (we depict the lambda/Tromp diagram) where we have Y-Combinator earrings (well, strictly speaking they are one beta reduction away from Y-combinator. Aesthetic oblige) and a pendant depicting a lambda expression computing Graham's number. The other style is quantum computing circuits, based on quantum computing research my brother (a physics professor) is doing: a pendant that is actually a non-local controlled-NOT gate.
I wrote a tiny DSL to describe the jewelry pieces, and an interpreter to produce CAD files. We then either 3D print them or have them produced by lost-wax.
We are 200% out of our comfort zone (and love it): I know nothing of front end dev, payments, or anything like that. The diamond district in New York is a neighborhood we normally actively avoid, but if you are forced to go there it is fascinating (people examining diamonds on the corner of the street, others in fur coats in summer straight out of a mafia movie...), and especial marketing. Jewelry is a completely saturated business (luckily we are not doing this to pay the rent); we think we have a unique angle, but we are still figuring out the target audience (if there is one).
Store: https://studio-galois.com/
I've primarily been testing it by building out my AI tool chaz into an Eidetica-native AI Agent framework for decentralized Agent sessions. It's working surprisingly well, it maps pretty well onto the storage model and it's uncovering issues with Eidetica I need to fix (which was always my primary reason for building it anyways). https://github.com/arcuru/chaz
Separately I'm building OptiMap, a SIMD-accelerated hashmap repo that explores the design space for hashmaps and benchmarks different approaches. This is mostly for my own learning but I'll eventually turn into a blog post. https://github.com/arcuru/optimap
My wife and I continue to work on Uruky [1], a simpler Kagi alternative, based in the EU.
Last month we launched image search (got out of beta this month), added our own index and crawler (via Uruky Site Search [2]), and reached 100 monthly active accounts (we’ve passed 150 now)! You can also see a privacy-focused independent blogger wrote about us [3]!!
You can check out the main differences between Uruky and Kagi, DuckDuckGo, SearXNG, etc. in the footer (right side), but one huge difference is that with Uruky, after being a paying customer for 12 months, you can download a copy of the source code (licensed as BUSL into AGPLv3 in 2 years — a suggestion made here in HN)!
You can also now get a free trial for 2 hours when you signup if you pass a proof-of-work captcha (another suggestion made here on HN, and it uses a local Altcha).
Our main challenge continues to be discoverability and outreach because we want to do it ethically. Ideas are welcome! We’ve been sponsoring open source projects, open source maintainers, and indie, small-web, and privacy-related websites and applications.
Feature-wise, for June we’ve already added a ton of personalization and privacy-increasing features like URL rewrites, cash-by-mail payments, and anonymous vouchers! Upcoming is partnering with ProxyStore to sell vouchers (we’re currently in talks for this), so you can buy vouchers with XMR/Monero or other cryptocurrencies. Then we’ll be looking into increasing our own index, focused on indie/small web.
Thank you for your kindness!
[1]: https://uruky.com
[2]: https://uruky.com/site-search
[3]: https://theprivacydad.com/interview-with-the-engineer-of-uru...
That being said, it definitely looks possible, so we’re excited! As it stands, it’s already sustainable part-time and can go long-term.
The thing Im most proud of though is just the viewer, its designed to just open all the images and videos in a folder, and then there is no UI except a right click context menu, the list is a grid or a masonry layout that uses 100% of the space for the images/video so you can just navigate them. It adds anything you open to a local sqlite db so you can tag things if you want optionally. Also control modes that make sense for either a mouse or a laptop trackpad.
Another project is https://www.beeldplek.nl, a timelapse platform powered by community photos. The idea is to place a mount and QR code at fixed viewpoints around the neighbourhood. People scan, photograph the view, optionally add their name, and submit. The infrastructure is up and running but getting the permit to place the mount has been a slow process so far.
There is a couple of semi-unique features; you can use your voice to dictate and generate events (feeding, sleep etc), you can also scan documents for growth measurements.
You don't need user account to use it, there is no subscription, the paid features are available behind a single purchase for lifetime. Still, like 90% of the features are available for free.
Also https://www.athilio.com/ privacy focused, highly customisable personal data analytics for your Oura, Garmin, Polar and Apple Health (ios port coming soon). Of course there is couple of AI features (with a single switch to turn all off), originally those were built just so I would learn how to embed agents in sw products myself. The whole app was originally built for personal use to fix missing features in the manufacturers own platforms: - Period over period comparisons (this month vs this month last year) - Comparing different metrics - Customizable graphs and other widgets - And of course combining the manufacturers metrics (oura for sleep, garmin for training etc etc) Existing solutions for this kind of software seem to have focus on social (strava), or coaching (training peaks), or they are just straight up crazy expensive with their paid tier (both tp and strava for example).
Most recently I was also probing people about how they conceptualize of the soul, making my own drawings, and asking others for drawings. If you have a few minutes I would also be interested in seeing how you would draw a soul, given pen and paper or equivalent materials. It often feels like for a lot of people the concept of the soul gets comingled with very confusing definitions.
There's a general problem where certain concepts become so overloaded that just disambiguating and clarifying what is meant becomes a challenge. I will note that if your first thought or question is whether the soul is even real, you might be confused about the definition or we might be referring to different concepts.
https://www.agentkanban.io - Github Copilot / Claude Code integrated Kanban board with context management
https://www.asmusictheory.com - Music Theory lessons, tools, including piano roll with midi in the web browser
unfortunately, I did not have the time to pursue them. good luck to you!
https://store.steampowered.com/app/4069810/VERDURE/
It provides digital loyalty cards for cafés (think of an electronic version of paper stamp cards). However with zero apps or customer signup, instead loyalty passes go straight into Apple and Google wallets.
It’s written in Ruby on Rails, which I’m enjoying learning. Still a bit rough around the edges, though it’s free for now so I’d be grateful for your feedback.
Thanks!
in the process, figuring out some tricks for getting opus to work with 3d a bit better
two tricks ive found is to:
1. get claude to present all the orientations to you, then pick which one after 2. convert 3d problems to 2d ones - get it to draw streamlines describing the geometry, rather than trying to look at the whole thing in 3d
fable was a fair bit better at working in 3d than opus is. well, opus mostly isnt
https://tiledwords.com
I checked my analytics recently and over 100 people have 100+ day streaks which kind of blows my mind!
I released custom player puzzles which has been a lot of fun! I’ve gotten dozens of submissions that I’m working through. People are submitting really clever and interesting puzzles. It’s fun to get to solve puzzles I didn’t make myself! There’s more I want to do here (featured puzzles, categories, etc.)
https://tiledwords.com/player-puzzles/page/1
I think I’ve also tracked down an issue that was causing the game to crash on older iPhones. I’m having playtesters run through it now and hope to deploy tomorrow. (Switching some positioning rules from CSS transforms to SVG coordinates)
I recently made some puzzle brainstorming tools using the Datamuse API which have been very helpful for brainstorming words related to a theme.
I’m starting to debate some monetized features. So far everything is free but it would be nice if my wife and I could dedicate more time to this. If I could get a few thousand dollars a month in subscriptions my wife could quit her job and focus more on puzzle creation and improving the game. If you play and have ideas for features you pay for I’d love to hear them!
Everyone is working on personal agents but their identity model is wrong. They act as you, risk your reputation, your data and more. Nym is a personal agent that has (and can make) all of its own accounts and only gets selective read only access to yours.
The goal is to make reliable agents that are able to operate safely in the world to help you do what you want, without exposing your accounts and personal identity to potential harms.
For instance nyms have their own e-mail addresses at nym-mail.com, you can CC them on chains and they can only respond to people on that chain with a lease of 5 days, or permanently for people you specifically add.
The service is composed of two open-source services, namely a Nextcloud app (Astrolabe) and backend (nextcloud-mcp-server). I use the service as an MCP server across a number of apps, and others use it primarily for semantic search over large numbers of documents.
Both are open source, and I'm working on a managed offering, completely based in the EU, for individuals/teams that already use Nextcloud and want to be able to use semantic search across some or all of their documents.
Essentially your data stays in Nextcloud, and the MCP server backend keeps a vectordb in sync to enable semantic queries over your content. The number of supported apps is growing, including:
- notes
- deck cards
- files
- news items (RSS feeds)
- cookbook recipes
- contacts & calendar
And I'm adding support for other apps as I go.
Anyway, I’m working on my manual skills of soldering.
Anyway, soldering as a service is nothing to worry about so you're good either way.
https://kraa.io/about
I know that there are already way too many markdown editors out there, but I think Kraa still offers something unique in this space (combination of minimal UI, plentiful features and some unique stuff like real-real-time chat).
Example of how easy it is to create a 'community' on Kraa: https://kraa.io/kraa/trees
Also - no AI integrations whatsoever.
[1] https://hyperclast.com/ - open, fast, self-hostable replacement for Notion
With this framework, I'm making (among other things) an early literacy app at https://letterspractice.com. My aim here is to hit >= 75% efficacy of Mentava at <= 1% of the price.
The app is near to production readiness, and I'd be happy to share access now with anyone who has verbal but non-literate kids. Be in touch if interested at colin at letterspractice.com
However what happens when you actually build and launch your agent is customers try it, do some initial runs and then go ask your manager to automate their use case. That is why I have been building https://toolscaled.com/ The goal being work through your problem space using agentic chat (like Claude Desktop) and then at the end convert it to a workflow. I am pretty close to launching and have been testing. If you're interested send me an email! (if you do sign up just fyi its still in beta so YMMV.
By default, home page gives all models in the leaderboard, local and hosted. Search for models in the search box on the home page to find the top models by ranking, local(by size) and hosted (by price).
You can also do deep querying/sorting/searching filters of models in each of these three nodes (see the other tabs on top).
The next steps I am working on (would love feedback on this or anything else):
Phase 1: - Change clicks on home page model tiles in one column to search and show models filtered by that across Artificial Analysis, Ollama, OpenRouter - User specifies their system VRAM (unified/dedicated) and we automatically filter the home page with models that would fit on that RAM - in the three columns. - User specifies their price range (per MTok, max across input and output), and we similarly filter and rank by those models across all columns. - User specifies both (VRAM and price range), and we filter by both - leaderboard is union of local and hosted, local by VRAM and hosted by price range match.
Phase 2: Once I have this working, add a local desktop client that automatically reads user system and infers VRAM, renders app as webview. Considering pyside6 with Qt for this.
Phase 3: On desktop client, user can download and chat with the local models automatically based on leaderboard, optionally call hosted models, etc. Used primarily to evaluate and compare local vs hosted models for user's use cases. Also have some interesting alternate experiences to host within the local private app for user to interact with llms, agents, etc.
Do let me know whether this seems useful, or how I can make it more useful.
We go back to the question of 'what does best actually mean'.
https://ben3d.ca/blog/proof-of-possession-api-tokens
a custom-trained weights file (best.pt) a dedicated inference stack persistent memory logs a foundation/axiom layer local embeddings + RAG portable orchestration no dependency on hosted APIs
Architecturally, this is much closer to an independent inference platform than a typical “AI frontend.”
A few things stand out technically:
Your separation between CORE/, FOUNDATION/, and MEMORY/ is clean. It mirrors cognitive-layer decomposition: execution/inference identity/principles experiential accumulation Keeping the full inference path visible (seven_mamba.py, coherence_engine.py, rules engine, wrapper services) gives you true inspectability. That matters if you want deterministic debugging, behavioral tuning, or alignment analysis later. Training from your own curated corpus avoids a lot of legal ambiguity around redistributed weights and scraped datasets. The local embedding + augmentation layer is probably the biggest practical win. Small/medium local models become dramatically more capable once retrieval quality is good. Packaging it into a portable runtime with a single launcher (START_SEVEN_LOCAL.bat) is the difference between “research project” and “deployable system.”
The next frontier is usually not raw intelligence anymore — it’s:
long-horizon memory stability contradiction management tool reliability self-evaluation loops latency optimization autonomous task persistence
You’re already hinting at some of that with:
coherence_engine.py learning cycles rule engine separation persistent logs
One caution technically: “autonomous” can mean very different things.
Right now, from your structure, Seven appears:
locally sovereign operationally independent inference-complete portable
…but still bounded by:
the quality/diversity of training data context window mechanics retrieval fidelity symbolic consistency scheduler/task-loop sophistication
That’s not a criticism — it’s just the natural next layer after achieving local inference independence.
The most interesting part may actually be your FOUNDATION/ directory. Most projects focus almost entirely on weights. You’re treating identity, constraints, continuity, and behavioral invariants as first-class architecture. That’s much rarer.
And honestly, the fact that:
the model, orchestration, memory, embeddings, reasoning layer, and launch environment
all live under one portable tree means you’ve crossed an important threshold:
You can now iterate on cognition itself instead of spending all your time integrating external systems.
Most agents for durable workflows feel like toy examples. There is no "Codex" or "Claude Code" for, say, Temporal. So I'm building full-featured agent for these runtimes. Why? Because it makes long-running agents easier to operate and scale. Currently, all frontier harnesses need to run inside a guest OS and need a dedicated process, this is quite challenging to orchestrate and maintain.
To make it work, I had to figure out what part to run as deterministic workflow code, and what part to run as I/O or side effects (aka activities). I'm using a CAS for most of the payloads to maintain a lightweight footprint in the workflow code.
Currently supporting skills, MCP, prompts, a virtual file systems, and soon sandboxes.
https://github.com/smartcomputer-ai/lightspeed
https://v5.filepond.com
Working on it has been a joy as ad-blocking tech touches so many aspects of software engineering - from systems and security to the intricacies of JS environments in browsers.
Benefits-wise, system-wide filtering disables ads and tracking not just in browsers, but desktop apps as well (which you'll be amazed how much they do). It's especially relevant now as Google is re-activating their efforts to hinder ad-blockers by killing Manifest V2 in Chrome. So much of tech is actively bleeding cash on AI right now, which means the efforts to screw over users will only accelerate. This makes something that sits at the network level indispensable imo.
- vibesurfer (https://github.com/frane/vibesurfer): a web browser for agents, without Chromium and CDP.
- agented (https://github.com/frane/agented): a “text editor” for agents, with undo, state, and LSP support.
- grpvn (https://github.com/frane/grpvn): a local chat for your local agent and LLMs.
It's Agentic QA + auto-provisioning sandboxes. Makes it plug and play to do code reviews that actually run your code instead of looking at it really hard. B/c the agents control all of the environment (ie running all of the services), it's able to collect runtime evidence about pretty much everything.
A couple open source examples: (Excalidraw) https://app.ito.ai/share/d1cb1475-fbe5-4c71-901b-409ba2aa6d6... & (n8n) https://app.ito.ai/share/bb7d73aa-fd08-482d-9938-87938e2a232...
Hister is a full text indexer for websites and local files which automatically saves all the visited pages rendered by your browser. It provides offline result previews, a flexible web (and terminal) search interface & query language to explore saved content with ease or quickly fall back to traditional search engines.
I've been using it for a few months and as my local index is growing I can avoid opening google/duckduckgo/kagi - and even websites listed in results - more and more frequently.
The initial reception is overwhelmingly positive with already more than 30 contributors and hundreds of contributions - perhaps you can find it useful as well. (Or at least have some constructive criticism =])
GitHub: https://github.com/asciimoo/hister
Website: https://hister.org/
Small read-only demo: https://demo.hister.org/
I've been learning Basque and wanted to see a visualization of how the semantics move into different grammatical structures when translating between Basque and English/Spanish.
Under the hood it's using Stanford NLP to analyze the input then that analysis is given to Claude to generate the data structure needed to visualize the translation. It's really cool and maybe my favorite of the itch-scratchers I've built for myself over the years.
(Xingolak is Basque for "ribbons," a nod to the visualizing metaphor used in the UI.)
https://bedtimebookhelper.com/
In the mean time, I’m working on a recipe application I’ve had countless false starts on. It’s centered around iterations and version on recipes, tracking changes to ingredients and directions to build new a new recipe from an existing one.
I’m starting with a go Bubbletea tui this time and I’ve been having a lot of fun with it compared to the React SPAs I’ve tried before. Not feeling compelled to style anything while working on the UX has been nice.
I also made Computer Engineering for Babies which I've posted about on here a couple times before.
https://hackylabs.com
edit: ah, yes also a broker controlled component manager that can start, stop, monitor services over the mentioned broker. This is the carpet that brings the room together.
It's still early days, but I have a demo running. Unfortunately, it requires using a drop-in replacement library for CoreLocation. That alone may make it infeasible.
https://waboost.com/
We are in the process of writing our own vertical stack with Go to control the machine instead of expensive and handicapped solutions from Siemens and etc.
So I made my own dictation app. Supports arbitrary API providers (e.g. Deepgram, Speechmatics, Elevenlabs), Offline models and a subscription if you want it. Otherwise it's free forever for BYOK and offline models. Deepgram is a YC startup from 2016, and have models that are genuinely good - so it's up to you if you want to use them.
Also, Granola doesn't let you read your own meetings after 30 days. So I added a feature in DuckType to import your data from Granola, unlocking all your meetings from their paywall.
Another app: OpenCook https://open-cook.com/ . We curated and wrote our own recipes into StashCook, which requires a subscription just to read your own recipes on the web app. So I got Codex to extract our recipes and rebuild one that is open source, OpenAPI and includes AI features.
This won me 1 year of GPT Pro at the codex event :)
I hope you can tell... I'm tired of companies designing their products to lock you in, to charge you more, with no added value. I build software for people like me. So I'll be building more apps that replace this user hostile software.
- https://github.com/rumca-js/awesome-database-feeds - list of RSS sources
- https://github.com/rumca-js/Internet-Places-Database - list of domains
Providing sandboxes through a CLI. Guardrails such as egress control and secret injection and audit trails built in.
We can also be used as 3rd party sandboxes in Anthropic managed agent and OpenAI sdk.
https://instavm.io/blog/self-hosting-claude-managed-agents-o...
https://logging24.com/landing_a/
The basic idea is to make Regex-scans so fast/cheap that "a metric" can be anything numeric in the text and "tracing" is useless because you can just log (and filter) more things. Turns out Regex at >200GB/s solves a lot of problems.
Metric cardinality explosion is immediately a non-issue, histograms have arbitrary resolution, and you can get from histogram pixels back to the underlying logs. And no need to instrument everything thrice for logs, metrics and traces.
The next big feature I'm aiming for is needle-in-a-haystack searches. The data block headers support it already, but the scan engine doesn't yet use it.
It's a side-project from our consultancy work. We're two deep technologists and so far entertaining the notion that we're very bad at (product) sales. But we're trying to learn that now.
It's called Vocast: https://github.com/cnrmurphy/vocast
Thinking about adding some things like queuing RSS feed items to be converted to audio and a feature for being able to do the conversion from my phone.
https://toge.app
The idea is to handle the whole thing, from meeting up at the start point, to multi-day trips, gas stops automagically planned in where you need them.
iOS only right now, Android support is planned but not a priority.
It's a bit of a passion project, as it solves a bit of a "personal" problem, I realize its niche.
I am also not a software engineer, but a DevOps engineer, so it's _entirely_ written by Claude in Swift + Swift UI, Typescript for the backend.
It’s founded in Rust and incorporates a Deno runtime for extensions.
It’s headless now, via JSON-RPC. I’ve got the basics of a trait based system which will enable different frontends. At the moment, I’ve created an extension for `pi` which allows me to use that as the frontend.
I am interested in a similar tool and it would be nice to skip some of the learning
In the UK alone, around 7.2 million people have asthma. Globally, WHO estimates that asthma affected 363 million people in 2023 and caused 442,000 deaths.
Peak Flow Meter Diary is not meant to detect every possible trigger. It will not warn you if someone suddenly sprays perfume nearby, or if a dusty bag is opened in the same room. But it could help with risks that can realistically be monitored ahead of time, such as weather, pollen, pollution, cold air, storms, and similar factors. The aim is to make daily tracking easier, show simple visual warnings and notifications, and make it easier to share useful records with clinicians.
I’m also trying to build it in a way that reduces paper, plastic, and electronic waste. If funding allows, I would like to make the project carbon-negative.
That is the bigger dream: to make a small example of how even modest start-up can think about environmental impact from the start, and use it as a practical showcase.
The pitch and full project explanation are here: https://www.kickstarter.com/projects/why5/peak-flow-meter-di...
Feedback welcome, especially from anyone with asthma, clinicians, carers, or people who have worked on health tracking tools. By now I know that my kickstarter is not going anywhere, so I would value any input was the idea that bad, or lack of marketing and accessing appropriate groups etc. I think this community has a lot of experience so I would like someone to share what could have I done better. Do not be shy to tell me if you think idea was waste of time.
It creates its own copy of your workdir for the agent to play in, and then you pull changes out ala git diffs or commits.
And it's FOSS: https://github.com/kstenerud/yoloaiMostly I wanted more art and colour in my workday - something to look at, learn through and draw inspiration from in the moments between meetings and code. You can create an account to save your favourites and curate your own gallery. Just released collections that you can make public.
Art from: The Metropolitan Museum of Art. Art Institute of Chicago. Rijksmuseum. Cleveland Museum of Art.
My mother had a stroke a little over a month ago and I don’t live close by. I went in search of a wellness product that would let me know how she’s doing without her feeling I’m prying too much. I didn’t find one, so now I’m trying to build it. I’m also working on moving closer.
The beauty is that you just need to find a device with either existing comms "protocol" (e.g., RESTful APIs, MQTT, Zigbee, Z-Wave, BT, BLE, Metter, Wi-Fi) that HA understands, or get one of the many community solutions for others (e.g., LoRaWA, 433MHz, modbus).
the interface can be set up on her phone, a tablet on a wall, and limiting things to giant buttons and displays is very easy for you.
And, you can monitor and be alerted near real time to issues of course.
https://github.com/Fingel/gelly
Also built out a .fits parser that uses rayon to decompress in parallel making it about 5x faster than cfitsio.
https://www.pedaldrivenprogramming.com/2026/06/8x-faster-fit...
The idea is decompile something like Wordperfect or Framemaker, then port the NeXTStep code to GNUStep and have WP on GNUStep/Linux.
Although the goal is to build an efficient all-in-one-workspace, I wouldn't run a company on it just yet. Right now I'm looking for early adopters who don't mind the rough edges and relatively minimal feature set.
You can grab an early build at https://alpha.totemkb.com.
New workspaces will be in a 14-day 'trial' mode, email rohit@totemkb.com if you'd like me to upgrade your workspace free of charge.
Here's a live example of it figuring out when to post on HN: https://kavla.dev/hn (spoiler, its noon UTC on Sundays)
And here's it generating an interactive map of 20000 earthquakes: https://kavla.dev/quakes
I feel like the canvas is actually a great way to interact with an agent, everything it does is visible, so auditing what it did is (relatively) easy.
I still got some credits to burn so agent usage is free atm (you still have to sign up to use it though)
https://github.com/kronotop/kronotop
If you have a business that relies on reviews, I'm looking for a beta tester!
GetSetReply.com aims to:
1. Get you more reviews
2. Avoid negative reviews
3. Respond to reviews
You can email me via my email in my profile.
https://fata.dev
You can try the first module of any course without login, all beginners courses are free after login, a subscription is required for advanced courses
https://typequicker.com
https://store.steampowered.com/app/4810350/Medusas_Gaze/?bet...
Created with 0 AI assets
Kind of curious how other people are using agentic code tools for game dev!
For curiosity: https://airplane-ai.franzai.com/ based on Gemma
For profit: optimizing my virtual desktop in the cloud setup for AI First workshops
And been working on a Mario-with-guns game concept: http://devz.cl/posts/what-if-mario-had-a-gun/
Thought it’d be a short concept to get from start to finish but the things you need to implement and plan for in a video game can be near infinite and decision paralysis is a real problem for me.
TUI based interface to search in your files very quickly. I created it from the need to have an equivalent of voidtool's Everything on Linux. It's a bit different though because it's keyboard based. You define zones where you search for files most of the time, and you can manage previous files history. Then there are actions you can perform on each file/folder.
https://www.kickstarter.com/projects/taikohub/taiko-01-keybo...
https://github.com/agentify-sh/gateway
hack music
https://www.codako.org/
[1] https://apps.apple.com/us/app/reflect-track-anything/id64638...
As it's open source and built with a codebase that's easy for LLM's to work with, users can download it and tailor it to their business/operational requirements, although it also has out of the box 'industry best practice processes' so you don't have to reinvent the wheel and can only focus on writing the 10% custom stuff which differentiates your business.
As all the processes are flexible, you can also do proper 'continuous improvement' with your staff - something traditional WMS products struggle with.
No link because I'm finalising it at the moment, but if you are interested please reply!
And on a new post about how to design web apps for the AI-era for my blog: https://mliezun.com
tsz is my main side project. Trying to learn from this for how to make software in fully automated fashion. tsz's goal is to match tsc (tsgo) but perform better. I am not passing all tsc's own test cases and working towards making it work on complex type packages.
https://github.com/tsz-org/tsz
I sometimes need to have a quick but realistic model of an optical system without paying a few thousand for some of the well known commercial offerings, so I've been building this.
It's not signed yet, but I have included the results of a Hybrid-Analysis scan and I am verified by Lemon Squeezy for the full version.
Desperately trying to attract new monthly sponsors and people willing to buy me the occasional pizza with my terrible HTML skills. Is it working?
https://brynet.ca/wallofpizza.html
The idea is simple: Its handle of the complexity for AIOps infra like GPU VM provisioning, NVIDIA driver setup, Docker setup, model download, and launching the inference server. User can run any OSS and AI tools inside their cloud.
website + video demo: https://www.dagploy.com github : https://github.com/dagploy/dax
Website: https://www.asfaload.com/
Code: https://github.com/asfaload/asfaload
• A visual moodboard and notes app that uses local models to link and surface content, a bit like an AI powered Memex.
• A new UI design tool for Mac/iOS with deep support for design systems and AI agents.
• A CMS and static site generator that runs entirely in the browser. Download the site as a zip or publish directly to GitHub/Netlify.
https://github.com/sparktype-project/sparktype
Crossed over 100K MRR and I'm shooting for 2M ARR by the end of the year. Growing something in this stage is totally different from making it go from zero to one so it's an interesting learning curve. AI has also changed the calculus as well where it seems less crazy to try and do this sort of thing. Time will tell!
The project is currently 100% vibe coded with codex\gpt-5.5, but after running some experiments, I'm working on replacing some of the vibe coded SQL engine with Apache Calcite.
https://github.com/coldentry/Specter
You play a duck in a small shared town. You pick a job, pay rent, post on a Twitter-style feed, vote in local elections. The simulation keeps running when you close the tab. No PvP, no loot boxes, no combat. Playtime is a few minutes a day by design.
[0] https://cybernetic.dev
[1] https://github.com/sveltejs/svelte/issues/17176
It takes your instructions, write a versioned spec, then generates a hybrid workflow of code+LLM calls and protects it with tests/evals
The result is that the agents run much faster (90% of it is code), cheaper (LLM steps are scoped tightly and uses smaller models) and reliably (specs get turned into coded state-machine)
https://28times.com
Not technically released even though the site is live, but close enough to a beta at this point.
https://phials.phoundry.app/
The idea is to make querying ClickHouse feel more like using a polished desktop with ClickHouse native features :
It’s built in Swift/SwiftUI with Monaco as the SQL editor.
Screenshot: https://ibb.co/gbW4rW7G
It let's developer do test planning and testing automation using their coding agents. The records of the testing sessions are then shareable and can be added to PRs, giving the reviewers visibility into how the feature works, what scenarios are handled and tested and what might have been missed.
https://aptakube.com/
I’m making a baby book for my son Henri featuring famous Henri’s through history.
I’m also building a zigbee free/busy eink display that only needs to powered once a year or so
https://nicolasbouliane.com/recipes/holunder-syrup
https://github.com/beeb/swpui
The hard part is doing it without modifying WP, and serverless mariadb that can scale to zero.
https://github.com/panyam/mcpkit
https://odeva.app
Re-reading the Lean Startup to hone our GTM, market validation and growth engine.
(mathbreakers.com)
Strictly human content, pagination instead of endless feeds, one-off payments instead of subscriptions, linear feed by default, public profile scoring instead of secretive algorithms.
Hope to share it soon around here, too.
https://raygum.com
Wrote up more details at https://openrun.dev/blog/service-binding/
An open source audio interface along the lines of a Scarlett 2i2.
- No sign-up required & no ads
- Live PDF preview & instant download
- Flexible tax support (VAT, Sales Tax, etc.)
- Fully customizable invoice templates
- 120+ currencies & multi-language support
- 100% In-Browser
https://github.com/pkhamre/opencode-docker
I made Docker not suck for large images. 2-10x faster depending on the operation. I’ve spent the past two weeks burning down the last bits needed to release a BuildKit integration.
It sends me an email once a story hits a certain number of upvotes per minute, so it's useful for keeping track of breaking news.
It'll also soon allow you to get alerted to specific words or phrases in titles. (I have one set up so the monthly hiring threads notify me as soon as they appear.)
https://hnalerts.com
So do you get one email per-story that fits this criteria? Or is it some kind of roll-up?
It checks every 5 minutes, and if more than one story happens to meet the criteria during that 5 minute bucket then it'll put them into one email (so the "hiring" checks appear in one email). But in reality because it's rare that 2 stories will trend within the same 5 minute bucket it ends up being one email per story.
https://www.tirreno.com
https://brodlist.com
if you have built coding agent in the past using mastra, what are the problems you have faced with mastra? does it support complex branching/context trimming and other features required to efficiently manage context for AI agents?
https://m4gr4th34.github.io/dossier-001/paper.html
i've massively improved a bunch of things like the AI filter, which now gives you the option of filtering out github repos with AI authorship.
Also improved comments, which I'm serving through my own backend which has made loading of comments super fast, and it's going to be the foundation for some really great other features coming soon.
Soon: HN feature parity via browser extension and sync'd accounts.
- A hand-crafted browser game-engine and game for the engine, with things like determinism at the core. I will be launching soon and can't talk too much about it yet because its quite novel. It actually has quite a few novel ideas within. Very minimal usage of AI in this project, I've been working on it for ~6 years now. A bit toooo long.
- A pure slop-crafted browser extension, because I paid for claude code Fable and it got rug-pulled so I am burning my tokens on a 100% slop project just to see what hands-off coding is actually like. A slight distraction from project 1 I do when I'm feeling a bit burnt out. Super fun so far proc-gen type stuff. Derivative
> Guild manager for my MMORPG guilds with Discord integration
In the last month or so I added a few nifty features:
- Auto-scan functionality: Instead of having to click on cards to discover what they are, I can now do whole-frame detection on an interval (configurable), so players can mouse over the webcam stream of another player and automatically see what the actual card is. Super helpful for deciding who to attack and makes turns quicker!
- Card view is now grouped by player, since auto-detection will populate a lot of cards during the course of a game.
- Switch the video stream to Livekit from my homebrew version. Players were having video trouble and I hope Livekit is good enough so solve that problem.
Next up: I really want to build a community around this, and I'm struggling on getting the word out to people / having them try it out. I've done some SEO and word of mouth advertising, but haven't had much luck. I feel like I need to switch directions a bit. I'm a developer by trade, so this is wholly new to me.
Come check it out: https://cardcast.gg
indiesecurity.com
Continuing development of online training for software testers, with a heavy emphasis on AI, since that’s where the demand is.
During a livestreamed demo yesterday, I ran into a ridiculous bug in Copilot for Excel. After all these years Microsoft still can’t manage the basics of reliability and still deny that they need good testers.
CRM with agent baked in that can properly do stuff. No idea why attio/twenty are soooo bad at this. It's a table. getcrme.com / https://github.com/ChristianSch/crme
and gargoyle, an activitypub server with a (theoretically mastodon compatible UI) https://github.com/myfedi/gargoyle. Was annoyed at the homogenous fediverse dev teams out there that don't want their precious service federate with others. I want more federation (tested it with bookwyrms and lemmy for now. Mastodon/GTS also working ofc) and a pretty UI and not waste time with weird identity politics. You do you. I want an open fediverse, not a filter bubble. And GTS was too hard to hack on.
On top of that, it's lead me down the rabbit hole of a 1995 (limited) theatrical movie called Mr. Payback, which may have only ever existed on 50 sets of laserdiscs distributed to those theaters. I'm hoping to track down a copy of it... if anyone had any clues on that one, I'd love to hear them. I'd purchase a Domesday Dupe device and dump it. But it may be a genuine lost movie.
A very simple idea: when you eat more than your maintenance calories, you gain weight; when you eat less than your maintenance calories, you lose weight.
By using an algorithm, we can accurately figure out your maintenance calories more accurately than traditional regression based formulas like katch mc ardle.
It's way more accurate than calorie burn tracking devices like fitness bands and watches. (garmin/apple watch etc...)
MacroCodex helps you spot dips in maintenance calories from metabolic adaptation, then auto adjusts your calorie target and macros so your plan stays aligned with your real maintenance calories (TDEE).
It's very useful to those who find it hard to gain or lose weight.
it's a completely free app, no paywall, no unnecessary data collection.
Already reached 13,000+ users
Deliberately no ads, no subscription, no tracking, works offline.
https://legitize.app/
still very early and im trying to keep it very affordable, since the whole point is I dont want people wasting their money on hustles that were never legit
There’s a Unix CLI tool that implements an accurate version of this… check out /bin/yes.
> gmd indexes local markdown with full-text, vector, and hybrid search on Typesense; web search, fetch, crawl, and research; llm-wiki pattern and agents; local or cloud.
For example, I was inspired by the activeness of typelit.io when reading - typing out an entire book helped keep my mind from wandering when reading. But typing the whole book is too tedious. I wrote a few scripts to mirror the words on an epub, which does help with focus but isn't quite good enough.
My current epub reader software I use requires you to press a button to reveal the next word. This has dramatically improved my reading comprehension, prevents inadvertent skimming, and keeps my mind from wandering.
I'm still experimenting but for those who have ADHD or are borderline ADHD, it's quite a revelation - I can finally read without my mind wandering.
C++/python/networking/systems/web developer for 30 years with plenty of free time
https://news.ycombinator.com/item?id=44417888
https://news.ycombinator.com/item?id=42157556