What are you working on? Any new ideas that you're thinking about?
Discussion Highlights (20 comments)
slig
Puzzleship - https://www.puzzleship.com/ It's a daily puzzles website focused on logic puzzles at this moment. I have about 90 subscribers, and it's online since Dec/25.
shrink
https://e.ml A free inbrowser inbox for inspecting .eml (email) files. There are many one-off .eml viewers around but I found myself inspecting the same files many times which evolved into this concept of an inbrowser inbox. Plus, world's shortest domain (3 characters) and the domain is an exact match for the file extension, a fun novelty. Very easy to remember! https://milliondollarchat.com a reimagining of the million dollar homepage for the AI age. Not useful, but fun. A free to use chatbot that anyone can influence by adding to the context. The chatbot's "thoughts" are streamed to all visitors.
socialproof-dev
SocialProof ( https://socialproof.dev ) – a tool that helps service businesses collect written testimonials from happy clients via a shareable link. The insight: the friction in getting testimonials isn't that clients don't want to help – it's that a blank "leave a review" box produces mediocre one-liners. SocialProof guides them through structured questions ("what was your situation before?" / "what changed?") so you get a compelling before/after narrative automatically. Free tier: unlimited testimonials. Just launched and looking for feedback from anyone who deals with client testimonials.
miguelmichelson
I'm working on Rauversion https://github.com/rauversion/rauversion , an open platform for independent music communities that combines music publishing, events, and marketplace tools in a single place. Artists can upload tracks, albums, and playlists with metadata, audio processing (waveforms, analysis), and embeddable players with chunk-range loading to save bandwidth. It also includes ticketing for events (QR validation, Stripe payouts), streaming integrations (Twitch, Zoom, etc.), a magazine system for publishing articles, and a marketplace to sell music (digital or physical), gear, merch, and services. The goal is to give underground scenes a self-hosted infrastructure for releasing music, organizing events, and sustaining their communities.
absoluteunit1
TypeQuicker ( https://typequicker.com ) - personalized and engaging typing application. Anyone can learn to type fast - I think it just takes the right tools to make it interesting enough for the users to use daily
postatic
Working on... - Tablex ( https://www.tablex.pro ) - seat arrangement app for weddings, seminars, conferences. - Kardy ( https://www.kardy.app ) - group card app I've always wanted to build. - Jello ( https://www.jello.app ) - Create games with your own photos and sound effects!
dkoy
https://www.personalreach.ai/ Automated personal outreach app for job seekers, integrated with Gmail.
mindcrime
This weekend I spent a lot of time on an Agent Registry idea I wanted to try out. The basic idea is that you put your Agent code in a Docker image, run the container with a few specific labels, and the system detects the Container coming online, grabs the AgentCard, and stores it in the Registry. The Registry then has (in the current version) a REST interface for searching Agents and performing other operations. But once all the low level operations are done, my plan is to implement an A2A Agent as the sole Agent listed in the AgentCard at $SERVER_ROOT/.well-known/agent-card.json, which is itself an "AgentListerAgent". So you can send messages to that Agent to receive details about all the registered Agents. Keeps everything pure A2A and works around the point that (at least in the current version) A2A doesn't have any direct support for the notion of putting multiple Agents on the same server (without using different ports). There are proposals out there to modify the spec to support that kind of scenario directly, but for my money, just having an AgentListerAgent as the "root" Agent should work fine. Next steps will include automatically defining routes in a proxy server (APISIX?) to route traffic to the Agent container. And I think I'll probably add support for Agents beyond just A2A based Agents. And of course the basic idea could be extended to all sorts of scenarios. Also, right now this is all based on Docker, using the Docker system events mechanism, but I think I'll want to support Kubernetes as well. So plenty of work to do...
rhoopr
icloudpd-rs - Fast iCloud Photos downloader, Rust alternative to icloudpd The original Python icloudpd is looking for a new maintainer. I’ve been building a ground-up Rust replacement with parallel downloads, SQLite state tracking, and resumable transfers. 5x faster downloads in benchmarks, single binary, Docker and Homebrew ready. https://github.com/rhoopr/icloudpd-rs
jascination
Deep link now ( https://Deeplinknow.com ) - deferred deep linking for developers / people who dont want their links blocked by adockers because Branch/Appsflyer et al are actually under-the-hood cross platform ad tracking services. I do no tracking, no analytics, just help you cross the airgap between web and mobile app so you can send users to the right place (and track them however you deem necessary)
dhuan_
mock, an API creation and testing utility. Any feedback is welcome. https://dhuan.github.io/mock/latest/examples.html
ChrisMarshallNY
I'm rewriting a shipping app, that is just over two years old. This is a "full rewrite," because I need to migrate away from my previous server, which was developed as a high-security, general-purpose application server, and is way overkill for this app. Migration is likely to take a couple more years, but this is a big first step. I've rewritten the server, to present a much smaller API. Unfortunately, I'm not yet ready to change the server SQL schema yet, so "behind the curtain" is still pretty hairy. Once the new API and client app are stable, I'll look at the SQL schema. The whole deal is to not interfere with the many users of the app. I should note that I never would have tried this, without the help of an LLM. It has been invaluable. The development speed is pretty crazy. Still a lot of work ahead, but the server is done, and I'm a good part of the way through the client communication SDK.
tombert
A few things. I've been on/off working on a Forth compiler for the NES. It will be open source soon enough but I'm not happy with the code right now as it's extremely messy, repetitive, and buggy, but I think it's turning out ok. I am resisting the urge to use Claude to do all the work for me, since that's depressing. I've also been working on a clone of the old podcasting website TalkShoe. It's nothing too complicated. It's mostly an excuse to learn a bit more about Asterisk and telephony stuff. I'm hoping to have something fully usable in about a month or two. I forked the main MiSTer binary due to some disagreements I had with Sorg in how he's running things [1]. My fork was largely done by Codex and Claude, but the tl;dr of it is that it has automatic backup of your saves, tagging and versioning of your saves, and it abuses the hell out of SQLite to give better guarantees of write safety than the vanilla MiSTer binary gives you. I've been using it for a few weeks now and it seems to work fine, and it's neat to be able to tag and version saves. I think that's mostly it. I'm always hacking on something so there might be a straggler there. [1] https://github.com/Tombert/Main_MiSSus/blob/master/README.md
stavros
I made my own AI personal assistant: https://github.com/skorokithakis/stavrobot It's like OpenClaw but actually secure, without access to secrets, with scoped plugin permissions, isolation, etc. I love it, it's been extremely helpful, and pairs really well with a little hardware voice note device I made: https://www.stavros.io/posts/i-made-a-voice-note-taker/
ryoung
https://fitcal.app syncs Strava activities to your Google calendar. No fancy features, just does what it says on the tin. Really fun to build out with elixir + phoenix. When training I like to have every day mapped out with how many miles to run, at what pace, etc as an event in my calendar. My actual workout gets uploaded into Garmin and Strava, but I always wanted it back in the calendar so I could see at a glance the consistency over time. It's been really fun to see other people use and get value out of something I built for myself.
kukkeliskuu
usm.tools https://usm.tools/public/landing/ - platform that allows defining services (the organizational kind) as data, allowing different stakeholders differemt views on them. For instance somebody participating in a service delivery can see how they contribute to it Arch Asxent https://github.com/mikko-ahonen/arch-ascent - tool for analyzing large microservice networks with hundres of microservices and creating architectural vision for them, and steps to reach the vision
antoineMoPa
Training a tiny LLM for fun using Rust/Candle - I constantly tweak stuff and keep track of results in a spreadsheet and work on generating a bigger corpus with LLMs. It's a project for fun, so I don't care about finding actual human generated text, I'd rather craft data in the format I want using LLMs - Probably not the best practice, but I can sleep properly despite doing that. My favorite output so far is that I asked it what life was and in a random stroke of genius, it answered plainly: "It is.". It's able to answer simple questions where the answer is in the question with up to 75% accuracy. Example success: 'The car was red. Q: What was red? ' |> 'the car' - Example failure: 'The stars twinkled at night. Q: What twinkled at night? ' |> 'the night'. So nothing crazy, but I'm learning and having fun. My current corpus is ~17mb of stories, generated encyclopedia content, json examples, etc. JSON content is new from this weekend and the model is pretty bad at it so far, but I'm curious to see if I can get it somewhere interesting in the next few weeks. https://github.com/antoineMoPa/rust-text-experiments
philajan
I've been working on an app to track my son's 1000 books before kindergarten. I've also added QOL features like barcode scanning for adding books to the library and creating a rotation based on the last time the book was read and whether I actually enjoy reading it. (The books I don't like make it through the rotation just with less frequency.) This was an excuse to ship a mobile app for the first time and get familiar with supabase. After these last few bugs are fixed, its ready for a semi-public TestFlight with our friends who have kids.
skrig
We're building a new CRM from the ground up. We've helped a handful of companies and non-profits set up CRMs and it's amazing how bad existing CRMs are. It's like they don't understand what common day to day tasks need to be made as easy as possible. We're also trying to use AI more thoughtfully than just bolting on a chatbot. We're planning to consider each workflow our customers need and how AI might help speed them up - even letting them build custom AI workflows. I think most businesses (especially smaller businesses) don't want to work at the level of Claude Code, Codex, etc. They want to work on higher level problems - build this dashboard, connect these data sources, invoice this customer, etc. Aside from that, we've noticed that the basics really matter, so we're trying to nail that first. We're definitely a bit delusional, we're just 3 people, we're doing it without funding and the competition is stiff, but we really believe in the product. Additionally, I think a lot of CRMs go south by taking on too much VC that naturally pushes them to prioritize ROI instead of continually improving the product.
lpellis
https://pagewatch.ai/ - make sure LLM's can understand your site. There is a surprising amount of edge cases that can cause ChatGPT or others to misunderstand your pages. Some models can handle div based tables, some want alt tags but cannot understand title tags, etc. I built the tool to check your site as close as possible to what a human would see and then compare it with LLM's. It was a weird journey trying to tease this info out of the models, they will happily lie, skip checking sites or just make things up.
Related Discussions
Found 5 related stories in 53.0ms across 3,471 title embeddings via pgvector HNSW
Discussion Highlights (20 comments)
slig
Puzzleship - https://www.puzzleship.com/ It's a daily puzzles website focused on logic puzzles at this moment. I have about 90 subscribers, and it's online since Dec/25.
shrink
https://e.ml A free inbrowser inbox for inspecting .eml (email) files. There are many one-off .eml viewers around but I found myself inspecting the same files many times which evolved into this concept of an inbrowser inbox. Plus, world's shortest domain (3 characters) and the domain is an exact match for the file extension, a fun novelty. Very easy to remember! https://milliondollarchat.com a reimagining of the million dollar homepage for the AI age. Not useful, but fun. A free to use chatbot that anyone can influence by adding to the context. The chatbot's "thoughts" are streamed to all visitors.
socialproof-dev
SocialProof ( https://socialproof.dev ) – a tool that helps service businesses collect written testimonials from happy clients via a shareable link. The insight: the friction in getting testimonials isn't that clients don't want to help – it's that a blank "leave a review" box produces mediocre one-liners. SocialProof guides them through structured questions ("what was your situation before?" / "what changed?") so you get a compelling before/after narrative automatically. Free tier: unlimited testimonials. Just launched and looking for feedback from anyone who deals with client testimonials.
miguelmichelson
I'm working on Rauversion https://github.com/rauversion/rauversion , an open platform for independent music communities that combines music publishing, events, and marketplace tools in a single place. Artists can upload tracks, albums, and playlists with metadata, audio processing (waveforms, analysis), and embeddable players with chunk-range loading to save bandwidth. It also includes ticketing for events (QR validation, Stripe payouts), streaming integrations (Twitch, Zoom, etc.), a magazine system for publishing articles, and a marketplace to sell music (digital or physical), gear, merch, and services. The goal is to give underground scenes a self-hosted infrastructure for releasing music, organizing events, and sustaining their communities.
absoluteunit1
TypeQuicker ( https://typequicker.com ) - personalized and engaging typing application. Anyone can learn to type fast - I think it just takes the right tools to make it interesting enough for the users to use daily
postatic
Working on... - Tablex ( https://www.tablex.pro ) - seat arrangement app for weddings, seminars, conferences. - Kardy ( https://www.kardy.app ) - group card app I've always wanted to build. - Jello ( https://www.jello.app ) - Create games with your own photos and sound effects!
dkoy
https://www.personalreach.ai/ Automated personal outreach app for job seekers, integrated with Gmail.
mindcrime
This weekend I spent a lot of time on an Agent Registry idea I wanted to try out. The basic idea is that you put your Agent code in a Docker image, run the container with a few specific labels, and the system detects the Container coming online, grabs the AgentCard, and stores it in the Registry. The Registry then has (in the current version) a REST interface for searching Agents and performing other operations. But once all the low level operations are done, my plan is to implement an A2A Agent as the sole Agent listed in the AgentCard at $SERVER_ROOT/.well-known/agent-card.json, which is itself an "AgentListerAgent". So you can send messages to that Agent to receive details about all the registered Agents. Keeps everything pure A2A and works around the point that (at least in the current version) A2A doesn't have any direct support for the notion of putting multiple Agents on the same server (without using different ports). There are proposals out there to modify the spec to support that kind of scenario directly, but for my money, just having an AgentListerAgent as the "root" Agent should work fine. Next steps will include automatically defining routes in a proxy server (APISIX?) to route traffic to the Agent container. And I think I'll probably add support for Agents beyond just A2A based Agents. And of course the basic idea could be extended to all sorts of scenarios. Also, right now this is all based on Docker, using the Docker system events mechanism, but I think I'll want to support Kubernetes as well. So plenty of work to do...
rhoopr
icloudpd-rs - Fast iCloud Photos downloader, Rust alternative to icloudpd The original Python icloudpd is looking for a new maintainer. I’ve been building a ground-up Rust replacement with parallel downloads, SQLite state tracking, and resumable transfers. 5x faster downloads in benchmarks, single binary, Docker and Homebrew ready. https://github.com/rhoopr/icloudpd-rs
jascination
Deep link now ( https://Deeplinknow.com ) - deferred deep linking for developers / people who dont want their links blocked by adockers because Branch/Appsflyer et al are actually under-the-hood cross platform ad tracking services. I do no tracking, no analytics, just help you cross the airgap between web and mobile app so you can send users to the right place (and track them however you deem necessary)
dhuan_
mock, an API creation and testing utility. Any feedback is welcome. https://dhuan.github.io/mock/latest/examples.html
ChrisMarshallNY
I'm rewriting a shipping app, that is just over two years old. This is a "full rewrite," because I need to migrate away from my previous server, which was developed as a high-security, general-purpose application server, and is way overkill for this app. Migration is likely to take a couple more years, but this is a big first step. I've rewritten the server, to present a much smaller API. Unfortunately, I'm not yet ready to change the server SQL schema yet, so "behind the curtain" is still pretty hairy. Once the new API and client app are stable, I'll look at the SQL schema. The whole deal is to not interfere with the many users of the app. I should note that I never would have tried this, without the help of an LLM. It has been invaluable. The development speed is pretty crazy. Still a lot of work ahead, but the server is done, and I'm a good part of the way through the client communication SDK.
tombert
A few things. I've been on/off working on a Forth compiler for the NES. It will be open source soon enough but I'm not happy with the code right now as it's extremely messy, repetitive, and buggy, but I think it's turning out ok. I am resisting the urge to use Claude to do all the work for me, since that's depressing. I've also been working on a clone of the old podcasting website TalkShoe. It's nothing too complicated. It's mostly an excuse to learn a bit more about Asterisk and telephony stuff. I'm hoping to have something fully usable in about a month or two. I forked the main MiSTer binary due to some disagreements I had with Sorg in how he's running things [1]. My fork was largely done by Codex and Claude, but the tl;dr of it is that it has automatic backup of your saves, tagging and versioning of your saves, and it abuses the hell out of SQLite to give better guarantees of write safety than the vanilla MiSTer binary gives you. I've been using it for a few weeks now and it seems to work fine, and it's neat to be able to tag and version saves. I think that's mostly it. I'm always hacking on something so there might be a straggler there. [1] https://github.com/Tombert/Main_MiSSus/blob/master/README.md
stavros
I made my own AI personal assistant: https://github.com/skorokithakis/stavrobot It's like OpenClaw but actually secure, without access to secrets, with scoped plugin permissions, isolation, etc. I love it, it's been extremely helpful, and pairs really well with a little hardware voice note device I made: https://www.stavros.io/posts/i-made-a-voice-note-taker/
ryoung
https://fitcal.app syncs Strava activities to your Google calendar. No fancy features, just does what it says on the tin. Really fun to build out with elixir + phoenix. When training I like to have every day mapped out with how many miles to run, at what pace, etc as an event in my calendar. My actual workout gets uploaded into Garmin and Strava, but I always wanted it back in the calendar so I could see at a glance the consistency over time. It's been really fun to see other people use and get value out of something I built for myself.
kukkeliskuu
usm.tools https://usm.tools/public/landing/ - platform that allows defining services (the organizational kind) as data, allowing different stakeholders differemt views on them. For instance somebody participating in a service delivery can see how they contribute to it Arch Asxent https://github.com/mikko-ahonen/arch-ascent - tool for analyzing large microservice networks with hundres of microservices and creating architectural vision for them, and steps to reach the vision
antoineMoPa
Training a tiny LLM for fun using Rust/Candle - I constantly tweak stuff and keep track of results in a spreadsheet and work on generating a bigger corpus with LLMs. It's a project for fun, so I don't care about finding actual human generated text, I'd rather craft data in the format I want using LLMs - Probably not the best practice, but I can sleep properly despite doing that. My favorite output so far is that I asked it what life was and in a random stroke of genius, it answered plainly: "It is.". It's able to answer simple questions where the answer is in the question with up to 75% accuracy. Example success: 'The car was red. Q: What was red? ' |> 'the car' - Example failure: 'The stars twinkled at night. Q: What twinkled at night? ' |> 'the night'. So nothing crazy, but I'm learning and having fun. My current corpus is ~17mb of stories, generated encyclopedia content, json examples, etc. JSON content is new from this weekend and the model is pretty bad at it so far, but I'm curious to see if I can get it somewhere interesting in the next few weeks. https://github.com/antoineMoPa/rust-text-experiments
philajan
I've been working on an app to track my son's 1000 books before kindergarten. I've also added QOL features like barcode scanning for adding books to the library and creating a rotation based on the last time the book was read and whether I actually enjoy reading it. (The books I don't like make it through the rotation just with less frequency.) This was an excuse to ship a mobile app for the first time and get familiar with supabase. After these last few bugs are fixed, its ready for a semi-public TestFlight with our friends who have kids.
skrig
We're building a new CRM from the ground up. We've helped a handful of companies and non-profits set up CRMs and it's amazing how bad existing CRMs are. It's like they don't understand what common day to day tasks need to be made as easy as possible. We're also trying to use AI more thoughtfully than just bolting on a chatbot. We're planning to consider each workflow our customers need and how AI might help speed them up - even letting them build custom AI workflows. I think most businesses (especially smaller businesses) don't want to work at the level of Claude Code, Codex, etc. They want to work on higher level problems - build this dashboard, connect these data sources, invoice this customer, etc. Aside from that, we've noticed that the basics really matter, so we're trying to nail that first. We're definitely a bit delusional, we're just 3 people, we're doing it without funding and the competition is stiff, but we really believe in the product. Additionally, I think a lot of CRMs go south by taking on too much VC that naturally pushes them to prioritize ROI instead of continually improving the product.
lpellis
https://pagewatch.ai/ - make sure LLM's can understand your site. There is a surprising amount of edge cases that can cause ChatGPT or others to misunderstand your pages. Some models can handle div based tables, some want alt tags but cannot understand title tags, etc. I built the tool to check your site as close as possible to what a human would see and then compare it with LLM's. It was a weird journey trying to tease this info out of the models, they will happily lie, skip checking sites or just make things up.