I’ve been working since the start of the year on a minimalist web reader (https://papercove.app) that I use every day to follow RSS feeds, newsletters and read-later, and that helps keep things from piling up.
I thought I’d get where I wanted much faster, but it turns out I ran into quite a few challenges: it’s quick to build something simple, but it takes much longer to get a reader that’s robust and pleasant to use (extraction, parsing, security, infrastructure, etc.).
On the tech side, I’m using my usual stack, Laravel and Livewire, with some Python for extraction and Go for the email infrastructure. This month I’m working on the beta release, since several people around me were already using it, so I’d like to gather more feedback.
That is a great landing page! I can relate on the velocity side, it can be quick to build a feature, but it takes time to get everything feeling right and usable.
I'm working on Hale, an abstract distributed systems language.
It's a traditional systems language in the sense that you have fine control over how resources are used, but it's abstract in the sense that you have to come to an agreement with the compiler about your intent around the resources, rather than directly declaring the machinery.
It's a distributed language in the sense that there is a higher level structural abstraction in the language that situates computations of the program within a recursive graph structure. Part of that structure incorporates message broker semantics. This gives the compiler a unified view of programs across arbitrary process boundaries. The structural abstractions also enable an effects+formal verification syntax within the language, which allows programmers to codify architectural decisions that are then checked by the compiler.
The compiler itself is infrastructure aware, and the highest layer of functionality it handles is configuring the environment into which applications deploy. The single language handles everything from individual memory allocations to distributed fleet deployments.
The language is close to v1, and I'm currently building a fully distributed inference-as-a-service application with it. Arbitrary hardware/supply matched against arbitrary callers/demand in real time.
I am currently on maternity leave with my first baby have just launched to the app store my first app!
I'm a product designer by trade and learnt to vibe code on Claude about a month ago now. I was weaning my baby and he developed a rash and haven't been able to work out what the pattern was causing it. So I created an app for weaning parents to log the food, add any reactions so when talking to their GP they can start to see a pattern and all advice, like nutrients, food variety, how to serve food all coming from the NHS and FSA.
Currently got 12 mums using the app and would love any feedback to make it even better! <3
I'm still working on making JustFax Online[1] more profitable. Added a bunch of features recently, as well as invisible improvements in fax routing, and admin stuff for myself to better analyze the traffic and patterns.
Other than this, I'm playing with vibe-coding stuff I always wanted to do but never had the time/skills to do. For example, I built a TUI on top of beancount that is tailored to my needs and my business[2]. I also completely got rid of self-hosted plausible and umami analytics, and replaced them with vibe-coded built-in-rust (c) analytics tool that relies on both js-beacon and streaming of caddy access.log. Will probably publish about it in my blog soon, so subscribe to the RSS if you want.
Lastly, I'm messing with self-hosting. I completely ditched Github and Gitlab for self hosted forgejo + actions runner. I set up proper backup plan for everything I care (documents, immich library, my SaaS DB, and the forgejo repositories).
I’m still working on https://feedsync.net, a tool to push RSS feed updates to Discord.
It’s been getting a decent number of sign ups despite me not really posting it anywhere or doing any marketing.
Ultimately a fun project, and useful for myself and a few friends, so I’m happy others are even interested in trying it.
I’ve started to regret using Phoenix LiveView, as it’s only deployed in one region, so high latency far from there. I’m exploring a SPA as a better alternative.
Otherwise, I’ve been playing around with a Lua engine to build feeds for websites that don’t support them, using AI to build the Lua as a once-off. It works reasonably well, but isn’t ready for prime time just yet.
A proportional width font terminal. "i" and "w" shouldn't take up the same amount of horizontal space. We used to have to do that because computers were slow and we counted cycles and every bits mattered. We live in a land of plenty now though so we can spend cycles doing math so that ls -l/top/etc table output is still aligned but "i" and "w" can take up the appropriate amount of horizontal space.
An opensource personal expense tracker, I was a happy user from an offline expense tracker which wiped my data when playstore decided auto-updating it,
I'm at the point where I'm finally actively using it to register my activity, it is straightforward to register tickets by sending them to a telegram bot, then, reconcile those by uploading my bank statement.
I'm trying to get the lowest possible usage friction so that I keep using it.
So far the better built pieces related to the data ingestion. Once this is good enough I'll build reports + anything coming to my head as a useful piece.
I'm leveraging AWS textract + bedrock + bda to parse bank statements. I expected this would have been easier but it is still a very complex problem which had required me to put many iterations (so far it works nicely with my own statements)
For ticket parsing, AWS textract + parsing rules has been enough.
Currently we are working on Kumoss Open Source, intent-based infrastructure platform that turns natural-language requests into infrastructure changes, while keeping validation, compliance and existing engineering workflows in the loop.
Basically allow developers to request any infrastructure need in a web portal and automatically that request is fulfilled following the organization standards the platform team defined.
A suite of high-dopamine games which use smart exercise bikes as the control interface.
When playing Zwift, Rouvy, etc, I find that I get too competitive and ruin longer workouts by trying to keep up with or sprint past people who are much faster than me over long distances.
This is bad for building stamina and endurance, but I get bored, and it's hard to fight boredom and physical strain both at once.
I do not get bored sitting in front of Balatro, Raccoin, Tetris - anything with bright colours and satisfying noises and combos.
The first finished prototype game is very simple: you sort coloured marbles. Higher watt output from the bike means marbles are blown, by wind, upwards as they roll across the screen. Lower watt output means they fall. Steady watt output means they move horizontally. Marble goes into correct hole -> satisfying noise. It rewards steady watt output over time, with minor adjustments, which is what I'm trying to work on right now.
I was pretty amazed by how engaging I found it (total iPad baby brain). The miles really fly by - I get tired before I get bored.
I think that next I'll either do a tower defence game, or a less-dopamine-rewarding game in the style of Kerbal Space Program. Taking your actual weight and watt output, putting a bike with wings into a physics engine, and the gameplay loop being unlocking increasingly large airplane pieces, and designing - then flying - increasingly ridiculous airborne bicycles seems like a compelling idea, though less good for fitness.
The control surface being so limited - essentially one measurement which can either go up or down - is a really fun constraint for creativity.
There's something in this idea. you can actually tie it to a smart watch (Amazfit allow for custom apps trivially for such uses), and you have a bigger pool.
Thanks, yes, I agree - it really doesn't "feel like" exercise when you're being bombarded by dopamine rewards. Despite this, most "exercise games" leave me with the same feeling of boredom / "fake fun" I got from playing educational games on the computers in the IT room at school.
I'd love to try a similar approach to gamifying exercise on a smart watch. That's an even more fun problem, because (when running, for example) you don't even have a constantly-present screen to communicate dopamine to the player with. Perhaps some watches wouldn't even be able to provide sound feedback? I've never owned one. It's a really interesting constraint for game design.
I'm building an open-source "spatial workspace for directing AI coding agents like an engineering director".
I got overwhelmed by walls of text of parallel Claude Code sessions. This limited the sessions I could steer in parallel to maybe 5 or 6. I knew there had to be a better way, and I found one: A canvas per project. Work laid out as cards. An agent in a worktree per card. Chat condensed to WhatsApp-style back and forth, not a litany of tool calls. Result is usually a narrated demo video that I can comment on by voice to have the agent go another round. Remote-control from my phone. Remote workers to scale beyond my machine. Everyone I know who tried it has stuck with it so far.
Thesoapbox.email - a social experiment email lottery to see what people do when suddenly given enormous reach. Every day a new subscriber is drawn to email the whole list. It’s hit 10,000 views in a couple of weeks which is my most viral project so far.
The second - a personal AI learning platform built on recursive self improvement and tailored content to push my boundaries. I’m a lifelong learner and this unifies everything for me.
(Currently not public)
A small team and I are working on Sendery [1], a transactional email platform for product teams. We're trying to fix some of the headaches that come with managing product emails as companies scale: keeping track of hundreds of templates, maintaining consistent designs, coordinating changes between developers and marketing/ops, and managing everything across multiple languages is way more time consuming than it should be.
It's been a fun project to work on since it's been a pain point for myself on many projects, so I'm mostly just trying to solve my own set of problems and hoping other people find it useful too.
My husband created an AI-powered website, and I've been using it to generate engaging AI videos for social media. This not only helps promote his website (seedeo.ai) but also expands our website's content library, which gives me a great sense of accomplishment.
A private, paid, ad-free and personally customizable search engine: Uruky [1]. It was launched earlier this year and reached 400 MAUs and €2k MRR last month.
A simple EU static and app hosting service: PodBy [2]. It was launched last week, and is at €10 MRR.
An Obsidian plugin that turns handwritten reMarkable notes into searchable text. You can run the handwriting recognition locally on a Mac. The latest feature I added sends your highlights and margin notes from the tablet to Readwise. https://taggedsync.com
I wrote a children’s story in Galician about open source. It's told as a fable. I made it open source, and people are now helping translate it into Spanish and English.
I’m looking for ways to fund printing and distribute the book. If anyone has done something similar, I’d love to learn from your experience!
- hermitator, a tool to run multiple isolated AI agents for WhatsApp on a single machine, with idle agents using no RAM: https://www.encona.com/posts/hermitator/
- showntell, which allows your coding agent to explain things to you with a video that starts playing within a few seconds of you asking: https://www.encona.com/posts/showntell/
- a philosophy tutor (testing in private for now) that does 2:1 live philosophy lessons, each exploring a single topic (aimed at ~10yo kids). I've tested this successfully (i.e. two kids did an hour and they want to do it again), and am trying to make improvements.
Oh, showntell is nice! I'll try incorporating it into my project (obeya.si), which already uses demo videos to show me work it did. But when I ask a question, the response is still just text. Could be so much better with your solution.
I am building Abbox trying to help engineers focus longer on tasks without being interrupted by non-technical people with small requests.
I always got annoyed by change this h1 to h2, add tracking to share button, why can’t the customer play the video, the styles don’t match figma.
If you are engineer who also gets distracted I would love to hear your opinion and feedback. It is a bit hard to put it all together as every department has his own needs and opinion about the website.
Magic AI - I'm using it as a sanitized kids chatgpt for 7 activities: Story, image creation, chat, reflections, journal, learn and quizzes. Sends me daily summary on Whatsapp.
It started with building pi in the cloud - with pure cloud flare workers. I have it working now, and can spin up - the wrangler agent can fully run it as long as you pass it an inference key, including a file view, a chatgpt like experience, and ability to build and host custom apps. Can use alarms to wake up to do plain language tasks, etc.
Trying to figure out how to package this up, and where this would even be useful for other apps.
Still working away on my book (and library book) recommendations service https://leafle.org
It has if nothing else been very useful for me (it has correctly deduced that I would get something out of borrowing Grief is the Thing With Feathers, the Dispossessed, and Cosmicomics, none of which I would have thought of reading). Plus it has been a fun opportunity to play around with LLMs as an interface and a research and reverse engineering tool; as well as Jev for non-user facing quality work like banning crap openrouter providers based on their output before putting it in front of a user.
Most recently I’ve been dropping off flyers for it at a few local libraries in my area.
I've been building out a link blog idea called Linked List that I've wanted for a long time. Curation will be even more important in the future and I would love to have another option beyond Hacker News and Lobsters to find good reads suggested by fellow humans. It has been a fun space to explore ideas.
Not quite ready to open up sign-ups, but you can get an idea of the site here: https://linkedl.ist/@kale
I'm vibing an old style RTS game and exploring how far can I get with local models for drawing, 3D models, rigging and sprites. I love how much I can accomplish with Claude in terms of code, but gluing it all together with graphics still requires plenty of "manual" work.
I've been working on an Obsidian plugin to quickly enter caloric and nutritional data (https://www.github.com/Krishna-Sivakumar/joule). The core features are done (A DSL and a runtime for finding and resolving formulae recursively), and I need to work on documentation and some convenience features. Hoping to finish it this month!
Maintaining my indie social network for tech people https://stackness.dev/ (currently struggling to keep users on the platform, even games and achievements didn't help, can you believe that? :D)
and this weekend I'll finally launch a tool for guitarists and their friends https://kantamigo.com/
Werkbook (https://werkbook.app), digital forms and photo reports for field crews. I'm a solo Rails dev, and thanks to Claude it now has native iOS and Android apps instead of Hotwire Native web-view wrappers.
I am building a system that connects texts (books, research papers, etc.) in a meaningful way to help people decide what to read and be aware of how texts relate to each other.
I'm so fucking tired. I built this tool, it's great, I love it, but its full capabilities are too complex to udnerstand. Because of that I struggle with marketing, as everyone is too lazy to try it out. Because of that I get no feedback, nothing to improve, and I can't make the tool any simpler, as otherwise it defeats the magic behind it.
Software is complicated by nature. It's our job to make it easy for the user.
Take a look at FFmpeg as an example. It's a complex tool that can do most things audio/video. A power user can do magical things, but they still provide simple commands for the most basic use-cases like conversion or trimming.
I've been working on online payment rails for businesses, developers and agents called Tuppence (https://tuppence.ai).
Accept online card payments from just 0.79% (UK) and earn 0.89% on all card spend [1], or get paid out to your bank.
I'm building tuppence to be available in the US, and 20 EU countries.
I'm getting a Point of Sale (POS) manufactured in the UK [2] for those who want to accept payments in person with card readers.
My goal is to help people sell their goods and make a living without paying over the odds for the privilege.
I charge a competitive fee for payment processing, give money back on card spend (with no cashback caps/limits) and do not charge saas fees or lock people into contracts.
Tuppences currently allows people to sell online with a store builder, expense management, payment links, direct debits & bookings - essentially Tuppence is a 'business' layer on top of what you get from the likes of Stripe, Adyen and Checkout.com. There's also have a 'connect' platform, so you can roll this out to your marketplace business.
Next on my roadmap is ticketing and 'treasury'. Treasury i'm personally excited about as you'll be able to earn 4% yield on your earnings, FDIC Insurance (FSCS in the UK), multi-currency banking in fiat balances such as USD, EUR, and GBP, or stablecoin balances like OUSD and USDC, and have bank account numbers to send or receive funds.
---
It's brand new, i'm still testing payment -> payout flows. These take a little time to verify on live payment rails.
Happy to give some fee-free payment processing for those who reach out and want to be early adopters, I can be reached at ollie@tuppence.ai, or comment on thread.
---
Tech Stack TLDR:
* TypeScript monorepo covering the API, dashboard, docs, mobile app and SDKs.
* The API runs on Ts.ED over Express with TypeORM and Postgres.
* Background jobs use pg-boss, so the queue lives in Postgres and there’s no Redis or separate broker.
* The dashboard, till and storefront are React + Vite + Tailwind, the docs and help centre are Astro, and the mobile app is React Native/Expo. We ship SDKs for Node, Python, iOS, Android, React Native and WordPress, plus an MCP server and agent tools.
* Everything runs on Google Cloud Run and Cloud SQL.
For years, I struggled to make any headway with Linux - I get so frustrated at how obscure, inscrutable, and unintuitive TUIs are! God I don’t want to waste my life typing esoteric strings of commands into the terminal. When I started with computers that was all there was, and once GUIs happened I never looked back.
Good news though, these days Claude will just do it for me!
I’ve been working on setting up a home media server, using headless Debian on a pi - I’ve got it set up to stream music and videos, hold all my ROMs, I’ve got it automatically standardizing file names and handling tagging and subtitles - all attached to a big 6-drive enclosure that I just stuffed all my random old HDDs into.
Even though I haven’t written more than a dozen lines of code or commands for the whole thing, I am pretty fuckin pleased that now I can just wave a magic wand and say “I want all my video game soundtracks filed under the game name rather than the artist” and Claude uh finds a way to grant my wish. I spend about an hour each night tweaking it and it’s so easy to customize to be exactly what I need.
I’ve been working since the start of the year on a minimalist web reader (https://papercove.app) that I use every day to follow RSS feeds, newsletters and read-later, and that helps keep things from piling up.
I thought I’d get where I wanted much faster, but it turns out I ran into quite a few challenges: it’s quick to build something simple, but it takes much longer to get a reader that’s robust and pleasant to use (extraction, parsing, security, infrastructure, etc.).
On the tech side, I’m using my usual stack, Laravel and Livewire, with some Python for extraction and Go for the email infrastructure. This month I’m working on the beta release, since several people around me were already using it, so I’d like to gather more feedback.
That is a great landing page! I can relate on the velocity side, it can be quick to build a feature, but it takes time to get everything feeling right and usable.
I'm working on Hale, an abstract distributed systems language.
It's a traditional systems language in the sense that you have fine control over how resources are used, but it's abstract in the sense that you have to come to an agreement with the compiler about your intent around the resources, rather than directly declaring the machinery.
It's a distributed language in the sense that there is a higher level structural abstraction in the language that situates computations of the program within a recursive graph structure. Part of that structure incorporates message broker semantics. This gives the compiler a unified view of programs across arbitrary process boundaries. The structural abstractions also enable an effects+formal verification syntax within the language, which allows programmers to codify architectural decisions that are then checked by the compiler.
The compiler itself is infrastructure aware, and the highest layer of functionality it handles is configuring the environment into which applications deploy. The single language handles everything from individual memory allocations to distributed fleet deployments.
The language is close to v1, and I'm currently building a fully distributed inference-as-a-service application with it. Arbitrary hardware/supply matched against arbitrary callers/demand in real time.
https://github.com/hale-lang/hale https://github.com/hale-lang/voice
I am currently on maternity leave with my first baby have just launched to the app store my first app!
I'm a product designer by trade and learnt to vibe code on Claude about a month ago now. I was weaning my baby and he developed a rash and haven't been able to work out what the pattern was causing it. So I created an app for weaning parents to log the food, add any reactions so when talking to their GP they can start to see a pattern and all advice, like nutrients, food variety, how to serve food all coming from the NHS and FSA.
Currently got 12 mums using the app and would love any feedback to make it even better! <3
https://apps.apple.com/gb/app/niblet-weaning-diary/id6822680...
https://getniblet.app
I'm still working on making JustFax Online[1] more profitable. Added a bunch of features recently, as well as invisible improvements in fax routing, and admin stuff for myself to better analyze the traffic and patterns.
Other than this, I'm playing with vibe-coding stuff I always wanted to do but never had the time/skills to do. For example, I built a TUI on top of beancount that is tailored to my needs and my business[2]. I also completely got rid of self-hosted plausible and umami analytics, and replaced them with vibe-coded built-in-rust (c) analytics tool that relies on both js-beacon and streaming of caddy access.log. Will probably publish about it in my blog soon, so subscribe to the RSS if you want.
Lastly, I'm messing with self-hosting. I completely ditched Github and Gitlab for self hosted forgejo + actions runner. I set up proper backup plan for everything I care (documents, immich library, my SaaS DB, and the forgejo repositories).
[1] https://justfaxonline.com
[2] https://kudmitry.com/articles/after-14-years-i-finally-built...
I’m still working on https://feedsync.net, a tool to push RSS feed updates to Discord.
It’s been getting a decent number of sign ups despite me not really posting it anywhere or doing any marketing.
Ultimately a fun project, and useful for myself and a few friends, so I’m happy others are even interested in trying it.
I’ve started to regret using Phoenix LiveView, as it’s only deployed in one region, so high latency far from there. I’m exploring a SPA as a better alternative.
Otherwise, I’ve been playing around with a Lua engine to build feeds for websites that don’t support them, using AI to build the Lua as a once-off. It works reasonably well, but isn’t ready for prime time just yet.
A proportional width font terminal. "i" and "w" shouldn't take up the same amount of horizontal space. We used to have to do that because computers were slow and we counted cycles and every bits mattered. We live in a land of plenty now though so we can spend cycles doing math so that ls -l/top/etc table output is still aligned but "i" and "w" can take up the appropriate amount of horizontal space.
An opensource personal expense tracker, I was a happy user from an offline expense tracker which wiped my data when playstore decided auto-updating it,
I'm at the point where I'm finally actively using it to register my activity, it is straightforward to register tickets by sending them to a telegram bot, then, reconcile those by uploading my bank statement.
I'm trying to get the lowest possible usage friction so that I keep using it.
So far the better built pieces related to the data ingestion. Once this is good enough I'll build reports + anything coming to my head as a useful piece.
I'm leveraging AWS textract + bedrock + bda to parse bank statements. I expected this would have been easier but it is still a very complex problem which had required me to put many iterations (so far it works nicely with my own statements)
For ticket parsing, AWS textract + parsing rules has been enough.
I wrote a bit more on my blog https://alexitc.com/blog/2026-10-16-opensourcing-my-expense-...
Repo at https://github.com/AlexITC/expense-tracker/
Currently we are working on Kumoss Open Source, intent-based infrastructure platform that turns natural-language requests into infrastructure changes, while keeping validation, compliance and existing engineering workflows in the loop.
https://github.com/InditexTech/kumoss
Basically allow developers to request any infrastructure need in a web portal and automatically that request is fulfilled following the organization standards the platform team defined.
Any feedback or comment is more than welcomed!
Any feedbac
A suite of high-dopamine games which use smart exercise bikes as the control interface.
When playing Zwift, Rouvy, etc, I find that I get too competitive and ruin longer workouts by trying to keep up with or sprint past people who are much faster than me over long distances.
This is bad for building stamina and endurance, but I get bored, and it's hard to fight boredom and physical strain both at once.
I do not get bored sitting in front of Balatro, Raccoin, Tetris - anything with bright colours and satisfying noises and combos.
The first finished prototype game is very simple: you sort coloured marbles. Higher watt output from the bike means marbles are blown, by wind, upwards as they roll across the screen. Lower watt output means they fall. Steady watt output means they move horizontally. Marble goes into correct hole -> satisfying noise. It rewards steady watt output over time, with minor adjustments, which is what I'm trying to work on right now.
I was pretty amazed by how engaging I found it (total iPad baby brain). The miles really fly by - I get tired before I get bored.
I think that next I'll either do a tower defence game, or a less-dopamine-rewarding game in the style of Kerbal Space Program. Taking your actual weight and watt output, putting a bike with wings into a physics engine, and the gameplay loop being unlocking increasingly large airplane pieces, and designing - then flying - increasingly ridiculous airborne bicycles seems like a compelling idea, though less good for fitness.
The control surface being so limited - essentially one measurement which can either go up or down - is a really fun constraint for creativity.
There's something in this idea. you can actually tie it to a smart watch (Amazfit allow for custom apps trivially for such uses), and you have a bigger pool.
Thanks, yes, I agree - it really doesn't "feel like" exercise when you're being bombarded by dopamine rewards. Despite this, most "exercise games" leave me with the same feeling of boredom / "fake fun" I got from playing educational games on the computers in the IT room at school.
I'd love to try a similar approach to gamifying exercise on a smart watch. That's an even more fun problem, because (when running, for example) you don't even have a constantly-present screen to communicate dopamine to the player with. Perhaps some watches wouldn't even be able to provide sound feedback? I've never owned one. It's a really interesting constraint for game design.
I'm building an open-source "spatial workspace for directing AI coding agents like an engineering director".
I got overwhelmed by walls of text of parallel Claude Code sessions. This limited the sessions I could steer in parallel to maybe 5 or 6. I knew there had to be a better way, and I found one: A canvas per project. Work laid out as cards. An agent in a worktree per card. Chat condensed to WhatsApp-style back and forth, not a litany of tool calls. Result is usually a narrated demo video that I can comment on by voice to have the agent go another round. Remote-control from my phone. Remote workers to scale beyond my machine. Everyone I know who tried it has stuck with it so far.
https://github.com/sadilek/obeya
cool! I will try it
Two main side projects lately:
Thesoapbox.email - a social experiment email lottery to see what people do when suddenly given enormous reach. Every day a new subscriber is drawn to email the whole list. It’s hit 10,000 views in a couple of weeks which is my most viral project so far.
The second - a personal AI learning platform built on recursive self improvement and tailored content to push my boundaries. I’m a lifelong learner and this unifies everything for me. (Currently not public)
A small team and I are working on Sendery [1], a transactional email platform for product teams. We're trying to fix some of the headaches that come with managing product emails as companies scale: keeping track of hundreds of templates, maintaining consistent designs, coordinating changes between developers and marketing/ops, and managing everything across multiple languages is way more time consuming than it should be.
It's been a fun project to work on since it's been a pain point for myself on many projects, so I'm mostly just trying to solve my own set of problems and hoping other people find it useful too.
[1] https://sendery.co
My husband created an AI-powered website, and I've been using it to generate engaging AI videos for social media. This not only helps promote his website (seedeo.ai) but also expands our website's content library, which gives me a great sense of accomplishment.
A private, paid, ad-free and personally customizable search engine: Uruky [1]. It was launched earlier this year and reached 400 MAUs and €2k MRR last month.
A simple EU static and app hosting service: PodBy [2]. It was launched last week, and is at €10 MRR.
Thank you for asking and for your suggestions!
[1]: https://uruky.com
[2]: https://podby.com
An Obsidian plugin that turns handwritten reMarkable notes into searchable text. You can run the handwriting recognition locally on a Mac. The latest feature I added sends your highlights and margin notes from the tablet to Readwise. https://taggedsync.com
I wrote a children’s story in Galician about open source. It's told as a fable. I made it open source, and people are now helping translate it into Spanish and English.
I’m looking for ways to fund printing and distribute the book. If anyone has done something similar, I’d love to learn from your experience!
Outside of my day job, I've been working on:
- hermitator, a tool to run multiple isolated AI agents for WhatsApp on a single machine, with idle agents using no RAM: https://www.encona.com/posts/hermitator/
- showntell, which allows your coding agent to explain things to you with a video that starts playing within a few seconds of you asking: https://www.encona.com/posts/showntell/
- a philosophy tutor (testing in private for now) that does 2:1 live philosophy lessons, each exploring a single topic (aimed at ~10yo kids). I've tested this successfully (i.e. two kids did an hour and they want to do it again), and am trying to make improvements.
- some other education-related things
- a jmail-style mailbox viewer: https://www.encona.com/posts/mailbox-viewer/
Oh, showntell is nice! I'll try incorporating it into my project (obeya.si), which already uses demo videos to show me work it did. But when I ask a question, the response is still just text. Could be so much better with your solution.
I am building Abbox trying to help engineers focus longer on tasks without being interrupted by non-technical people with small requests.
I always got annoyed by change this h1 to h2, add tracking to share button, why can’t the customer play the video, the styles don’t match figma.
If you are engineer who also gets distracted I would love to hear your opinion and feedback. It is a bit hard to put it all together as every department has his own needs and opinion about the website.
My email kamran.elchuzade@gmail.com
Magic AI - I'm using it as a sanitized kids chatgpt for 7 activities: Story, image creation, chat, reflections, journal, learn and quizzes. Sends me daily summary on Whatsapp.
It started with building pi in the cloud - with pure cloud flare workers. I have it working now, and can spin up - the wrangler agent can fully run it as long as you pass it an inference key, including a file view, a chatgpt like experience, and ability to build and host custom apps. Can use alarms to wake up to do plain language tasks, etc.
Trying to figure out how to package this up, and where this would even be useful for other apps.
Still working away on my book (and library book) recommendations service https://leafle.org
It has if nothing else been very useful for me (it has correctly deduced that I would get something out of borrowing Grief is the Thing With Feathers, the Dispossessed, and Cosmicomics, none of which I would have thought of reading). Plus it has been a fun opportunity to play around with LLMs as an interface and a research and reverse engineering tool; as well as Jev for non-user facing quality work like banning crap openrouter providers based on their output before putting it in front of a user.
Most recently I’ve been dropping off flyers for it at a few local libraries in my area.
I tried it out nd it looks nice!. It’s a great way to support local libraries and bookshops. I hope you have a ton of success!
Thanks! Hope it found you something interesting.
I've been building out a link blog idea called Linked List that I've wanted for a long time. Curation will be even more important in the future and I would love to have another option beyond Hacker News and Lobsters to find good reads suggested by fellow humans. It has been a fun space to explore ideas.
Not quite ready to open up sign-ups, but you can get an idea of the site here: https://linkedl.ist/@kale
I'm vibing an old style RTS game and exploring how far can I get with local models for drawing, 3D models, rigging and sprites. I love how much I can accomplish with Claude in terms of code, but gluing it all together with graphics still requires plenty of "manual" work.
Software development is dying. I am teaching myself how LLMs really really work with this tool that I am building https://modelmathics.com you can try it on https://try.modelmathics.com
Reflect [1], it’s a local-first privacy focused self tracking and data analysis app where you can set goals and run self experiments
[1] https://apps.apple.com/us/app/reflect-track-anything/id64638...
I've been working on an Obsidian plugin to quickly enter caloric and nutritional data (https://www.github.com/Krishna-Sivakumar/joule). The core features are done (A DSL and a runtime for finding and resolving formulae recursively), and I need to work on documentation and some convenience features. Hoping to finish it this month!
Maintaining my indie social network for tech people https://stackness.dev/ (currently struggling to keep users on the platform, even games and achievements didn't help, can you believe that? :D)
and this weekend I'll finally launch a tool for guitarists and their friends https://kantamigo.com/
https://arcaide.foo - to visualize the architecture of your (LLM's) code.
Werkbook (https://werkbook.app), digital forms and photo reports for field crews. I'm a solo Rails dev, and thanks to Claude it now has native iOS and Android apps instead of Hotwire Native web-view wrappers.
infra engineering meanwhile trying to build some stuff for my own. also trying to finish cs master’s
working on apyhub mcp: to enable all apyhub apis to be available for agents. https://apyhub.com/mcp
Adding tufting support to RapidCAM.app for CNC run makers. RapidCAM already supports 2.5D CNC, laser and rotary axis so tufting was a good fit.
I am building a system that connects texts (books, research papers, etc.) in a meaningful way to help people decide what to read and be aware of how texts relate to each other.
This sounds like a really cool project, do you have a repo or anything?
Not yet, but I am planning on making it open-source later.
I'm so fucking tired. I built this tool, it's great, I love it, but its full capabilities are too complex to udnerstand. Because of that I struggle with marketing, as everyone is too lazy to try it out. Because of that I get no feedback, nothing to improve, and I can't make the tool any simpler, as otherwise it defeats the magic behind it.
Software is complicated by nature. It's our job to make it easy for the user.
Take a look at FFmpeg as an example. It's a complex tool that can do most things audio/video. A power user can do magical things, but they still provide simple commands for the most basic use-cases like conversion or trimming.
https://www.clipcat.com/blog/how-to-use-ffmpeg-a-beginners-g...
1. Provide sensible defaults 2. Study user journeys and write simple manuals for them. 3. Ask friends or internet communities for feedback.
Don't get discouraged, you can do it!
I've been working on online payment rails for businesses, developers and agents called Tuppence (https://tuppence.ai).
Accept online card payments from just 0.79% (UK) and earn 0.89% on all card spend [1], or get paid out to your bank.
I'm building tuppence to be available in the US, and 20 EU countries.
I'm getting a Point of Sale (POS) manufactured in the UK [2] for those who want to accept payments in person with card readers.
My goal is to help people sell their goods and make a living without paying over the odds for the privilege.
I charge a competitive fee for payment processing, give money back on card spend (with no cashback caps/limits) and do not charge saas fees or lock people into contracts.
Tuppences currently allows people to sell online with a store builder, expense management, payment links, direct debits & bookings - essentially Tuppence is a 'business' layer on top of what you get from the likes of Stripe, Adyen and Checkout.com. There's also have a 'connect' platform, so you can roll this out to your marketplace business.
Next on my roadmap is ticketing and 'treasury'. Treasury i'm personally excited about as you'll be able to earn 4% yield on your earnings, FDIC Insurance (FSCS in the UK), multi-currency banking in fiat balances such as USD, EUR, and GBP, or stablecoin balances like OUSD and USDC, and have bank account numbers to send or receive funds.
---
It's brand new, i'm still testing payment -> payout flows. These take a little time to verify on live payment rails.
Happy to give some fee-free payment processing for those who reach out and want to be early adopters, I can be reached at ollie@tuppence.ai, or comment on thread.
---
Tech Stack TLDR:
* TypeScript monorepo covering the API, dashboard, docs, mobile app and SDKs. * The API runs on Ts.ED over Express with TypeORM and Postgres. * Background jobs use pg-boss, so the queue lives in Postgres and there’s no Redis or separate broker. * The dashboard, till and storefront are React + Vite + Tailwind, the docs and help centre are Astro, and the mobile app is React Native/Expo. We ship SDKs for Node, Python, iOS, Android, React Native and WordPress, plus an MCP server and agent tools. * Everything runs on Google Cloud Run and Cloud SQL.
References:
[1] Card issuing: https://tuppence.ai/cards [2] Point of sale: https://tuppence.ai/pos/ridge/
For years, I struggled to make any headway with Linux - I get so frustrated at how obscure, inscrutable, and unintuitive TUIs are! God I don’t want to waste my life typing esoteric strings of commands into the terminal. When I started with computers that was all there was, and once GUIs happened I never looked back.
Good news though, these days Claude will just do it for me!
I’ve been working on setting up a home media server, using headless Debian on a pi - I’ve got it set up to stream music and videos, hold all my ROMs, I’ve got it automatically standardizing file names and handling tagging and subtitles - all attached to a big 6-drive enclosure that I just stuffed all my random old HDDs into.
Even though I haven’t written more than a dozen lines of code or commands for the whole thing, I am pretty fuckin pleased that now I can just wave a magic wand and say “I want all my video game soundtracks filed under the game name rather than the artist” and Claude uh finds a way to grant my wish. I spend about an hour each night tweaking it and it’s so easy to customize to be exactly what I need.
[dead]
[dead]
[flagged]
[dead]
[dead]
[flagged]