alt Hacker NewsAsk HN: What are you working on? (January 2026)
What are you working on? Any new ideas that you're thinking about?
Comments
Spent about 2 years improving printing and scanning stack of Linux: CUPS, SANE, AirSane, as well as some legacy drivers, and also x86 proprietary driver emulation on ARM with Box86.
Even that "modern" printing stack in Linux is 20+ years old, there's still such an unbelievable amount of basic bugs and low-hanging-fruit optimizations, that it's kinda sad.
Not to mention that it still maintains ALL its legacy compatibility, as in supporting ≈5 different driver architectures, 4 user-selectable rasterizers (each with its own bugs and quirks).
The whole printing stack is supported by 4 people, 2 of whom are doing that since the inception of CUPS in 1999. Scanning is maintained by a single person.
Ubuntu 26.04 LTS is expected to be the last version with CUPS v2. CUPS v3 drops current printer driver architecture and introduces proper modern driverless printing with the wrapper for older drivers. Many open-source drivers are already use this wrapper, but expect a huge disarrangement from the users, as none of the proprietary drivers would work out of the box anymore.
Do you care about printing? Want to improve printing & scanning stack? Contact OpenPrinting! https://github.com/OpenPrinting/
Over the holidays I was building a wooden birdhouse with a Unifi Protect camera and a small web interface that automatically identifies the birds and shows me a simple overview over which type of bird visited how many times.
Birdhouse: https://img.notmyhostna.me/cRQ1gJfZCHjQKwFrgKQj
UI:
- https://img.notmyhostna.me/Hnw4qcvbg1ZQCrFxzGMn
- https://img.notmyhostna.me/62TFwSXSRRbCfxDz297h
- https://img.notmyhostna.me/40qhgHmSqQsrGr8BC7Db
- https://img.notmyhostna.me/9bgz4GYsjQH33n3MtWKp (Face labeling, so I can show thumbnails of the actual birds that visited and train a ML model on it in the future)
My meta side project for building other side projects: https://bodge.app/
I've always had a bunch of small side projects that I want to do that aren't worth the overhead required to actually put them together & keep them maintained. So, I built a small Lua-based FaaS platform to make each individual project less work whenever inspiration strikes. So far I've built:
* A current-time API for some hacked-together IoT devices: https://time.bodge.link/
* A script for my wife that checks her commute time and emails her before it's about to get bad.
* An email notification to myself if my Matrix server goes down.
* A 'randomly choose a thing' page. https://rand.bodge.link/choose?head&tails
* A work phone number voicemail, the script converts the webhook into an email to me.
* An email notification any time a new version is released for a few semi-public self-hosted services.
* Scrapers for a few companies' job listings that notify me whenever a new job is posted matching some filters.
* A WebPush server that I eventually want to use for custom notifications to myself.
* An SVG hit counter: https://hits.bodge.link/
Since I'm already maintaining it for myself, I figured I might as well open it up for others. It's free to play with, at least for now.
Random assortment of projects as time allows with the $JOB.
- Prototyping a cute little SSH-based sorta-BBS, inspired by the Spring '83 protocol, but terminal-centric rather than web-based. It's called Winter '78, and if we get another Great Blizzard this year, I'll be able to make some progress on it!
- Another prototype, for an experimental HPC-ish batch system. Using distributed Erlang for the control plane, and doing a lot of the heavy lifting with systemd transient units. Very much inspired by HTCondor as well as Joyent's (RIP to a real one) Manta.
After years of wondering what the post-UNIX paradigm of computing could look like, these past few months I've been prototyping a software platform built around capabilities and message passing, targeting Linux and bare-metal RISC-V. The big ideas I'm pursuing is a stackless design running on a flat address space with lightweight processes to minimize message-passing latency, and all the benefits of capabilities so every process is sandboxed and has only access to capabilities they have been explicitly passed via message passing.
I've also built a RISC-V emulator to integrate with this platform, so eventually it'll be able to run native binaries written in any language, completely sandboxed, completely built around message-passing. Basically a native, low-level BEAM-like platform to build an entire operating system and user-space.
While my day job is writing boring applications, this is the stuff that keeps me awake at night, and I would love so much to talk and write more about this, about the trial-and-errors I'm facing, but it's still so much in flux every week I'm exploring a new approach. Most of my work has been around the stackless scheduler, and I have a plan to achieve preemption for long-running or misbehaved tasks without having to compromise on memory usage (i.e. without giving each process its own stack and allocate memory for context switching).
Eventually I'd like to layer on top either Cap'n Proto or another high-performance serialisation system to create a distributed, introspectable environment of object-capabilities that are sending typed messages between each other, achieving the ultimate goal of creating an unholy hybrid between Smalltalk and the Erlang VM.
God, how I wish I was paid to work on this type of problems :-)
If this sounds close to your area of interests, please send me an email and I’d love to chat.
Script to auto-rename screenshots with Claude Code
I'm sure there are a ton of other projects out there that do this, but I couldn't find one that fit my needs exactly, so I threw this together in a few hours.
claude-image-renamer uses Claude Code CLI to analyze screenshots and rename them to something actually usable. It combines OCR text extraction with Claude's vision capabilities, so instead of "Screenshot 2025-12-29 at 10.03.10 PM.png" you get something like "vscode_python_debug_settings.png".
A few things it does:
Handles those annoying macOS screenshot filenames with weird Unicode characters
Uses OCR to give Claude more context for better naming
Keeps filenames clean (lowercase, underscores, max 64 chars)
Handles naming conflicts automatically
I’m genetically engineering yeasts to make subtly flavored breads. I’ve already done grape aroma, now working on wintergreen.
Also working on a red chamomile (using beat red biosynthesis). Just for fun. Red chamomile tea!
The idea is to have niche invite-only genetically engineered flavors that I can bring to parties around SF :) what’s more special than a genetically engineered organism that you can ONLY get if I’m there? Good calling card
Built a parking garage occupancy tracker for my city (https://www.parkeergaragesdelft.nl/) after a city council decision on car-free city center policies got delayed due to missing data. The city only publishes real-time availability with no historical record, so I started logging it. The site now shows historical data plus analysis of weekly patterns. (Note: website is in Dutch, but the charts should be self-explanatory.)
Now working on a second tool that monitors public reports on illegal dumping, broken streetlights and more. It tracks how long the municipality takes to resolve them
Lately, I've developed an interest in local politics and started reading policy documents, following city council meetings and even lobbied for a local park. Presenting public data clearly can help shape opinions and keeps the city council accountable, especially important with the upcoming city council elections.
Over the last two years I spent a surprising amount of time analyzing XSD files to understand regulatory changes in financial reporting. It was repetitive, painful, and unnecessarily manual.
In the past two months I built https://xsdviewer.com to make working with XML Schemas simpler: visual structure, navigation, diffing, and faster understanding of what actually changed between versions.
Right now I am iterating on new features and performance improvements. If you regularly work with XSDs or XML based standards and have ideas, pain points, or feature requests, I would love to hear them.
Been working on canine.sh for about 2 years now.
It’s an open source project that basically turns your kubernetes into a developer friendly PaaS.
Just crossed 2k apps on the cloud version, no idea how many people run it locally, and thanks to a generous sponsorship from the Portainer folks, I’m able to work on it close to full time.
I'm working on Tech Posts (https://techposts.eu), a Hacker News for Europe!
Since the last time I posted on HN it's gained a decent amount of traffic and users. I'm particularly happy with the jobs section, which is growing into a high signal-noise source for European tech jobs: https://techposts.eu/jobs
The reason I started this website is because so much incredible innovation and growth in Europe flies under the radar. If you ask Americans many will say it's just "banks and museums", stagnant, or worse. But the reality is there is a huge spectrum of exciting companies starting and growing here. We have space launch companies, battery companies, AI companies, and a whole bunch of other interesting stuff. It's an exciting time to be a European in tech!
VersionAlert: https://versionalert.com
For a couple of years now, I’ve wanted to build a service that lets you subscribe to new version notifications for any kind of software—desktop apps, drivers, packages, and more. As a Unity developer and consultant myself, I’ve always wanted to know the moment a new version becomes available. I value being at the bleeding edge, especially since a large part of the value I bring as a consultant comes from both the breadth and depth of my knowledge of the Unity engine.
That’s why I’m currently working on a niche version of the broader VersionAlert idea specifically for Unity, which is why the domain currently redirects to https://versionalert.com/unity .
The only other service I’ve found that really addresses this need is https://newreleases.io . I actually spoke with the very nice husband-and-wife team behind it and even offered to buy the whole project, but their asking price was about 10× higher than what I was offering—which I understand, no hard feelings. I still wish them the best of luck.
If anyone is aware of other projects or services in this space, I'd be happy to learn about them and chat.
Built my own Spotify recommendation egnine after getting tired of Spotify’s repetitive recommendations.
You get to choose the genres you're interested in, and it creates playlists from the music in your library. They get updated every day - think a better, curated by you version of the Daily Mixes. You can add some advanced filters as well, if you really want to customise what music you'll get.
It works best if you follow a good amount of artists. Optionally you can get recommendations from artists that belong to playlists you follow or you've created - if you don't follow much or any artists, then you should enable that in order for the service to be useful.
Working on WordPecker, trying to create something like a personalized Duolingo but for vocabulary you actually encounter.
Started when I was struggling to read books in English. Pushed an open source version back then (https://github.com/baturyilmaz/wordpecker-app), later added more features, and now working on a mobile app.
Recently started testing alpha version, fixing bugs and introducing new features right now (https://alpha.wordpeckerapp.com/).
My end goal is to build: an AI language learning companion that knows what you read, listen, and watch, knows you as a friend (real life, who you are), then helps you improve using that context. If you're B1 at language, it creates a personalized path to get you to B2, then C1, and so forth using your context.
words.saej.in
A site for filtering word lists and solving word puzzles
Anagrams, regular expression search, and a crossword helper, as well as several NYT word games.
I’m working on a free and open-source invoice generator: https://easyinvoicepdf.com/?template=stripe
Features:
- No Sign-Up Required + Instant PDF download
- Live PDF Preview
- Shareable Links
- Multiple Templates (incl. Stripe-style)
- Flexible Tax Support (VAT, GST, Sales Tax, and custom tax formats with automatic calculations)
- Multi-Language (Support for 10+ languages and all major currencies)
- Mobile-Friendly
GitHub: https://github.com/VladSez/easy-invoice-pdf
On holidays finished adding flexible tax support + other improvements: https://github.com/VladSez/easy-invoice-pdf/pull/163
Would love feedback, contributions, or ideas for other templates/features =)
I'm working on shipping the second batch of the Brighter Lamp, a lamp that's equal to ~30 normal lamps for daylight levels of light indoors.
We delivered our first 500 units last month and got positive reviews, but lots of small issues to straighten out.
I've spent the past ~year compiling a US nationwide land parcel dataset. I posted it to kaggle a few days ago: https://www.kaggle.com/datasets/landrecordsus/us-parcel-laye....
I'm around 99% coverage of the US. Learned a lot about land records and GIS along the way.
I've been working on a music-making website since late spring. This is my first real frontend project, and I'm writing it in pure Rust using Leptos (so far, haven't had to write a single line of JavaScript!)
Most of my work so far has been on the actual music-making interface, but I'm beginning work on the backend now. I've only worked with Django before (for a school project at Georgia Tech), so I'll be deep in the `sqlx` documentation for a while.
There's no manual, so use at your own risk (it's similar to tracker programs like FastTracker and OpenMPT): https://mondobe.com/tracker
I am working on a local RAG LLM designed for lower end PC's - ability for people to try out searching their own documents, seeing it was such a learning curve to get to this stage - hoping others can learn from my mistakes.
https://github.com/acutesoftware/lifepim-ai-core
Only been public a few days, so please let me know if there are glaring issues.
I'm working on a native MacOS Postgres client: http://github.com/ravelantunes/Searchlight I've been slowly chipping at it over the last couple of years as I find time, and I like it enough to already use it as my primary client (although still buggy here and there).
I've been working on a voxel engine in my spare time for 10 years, this year. I wrote everything from scratch, from the memory allocators, font rasterizer and a programing language all the way to collision detection, renderer and gameplay code. It's been a journey!
Working on https://chessnawk.vercel.app/ – a set of auto-grading tasks for middle school students learning programming.
Comes with Robot, Turtle, HTML/CSS (pixel diff tasks) and a gradual introduction into programming concepts. Currently on JS, literally right now GPT-5.2 helps me adding Python.
I've integrated a simplified clone of Replicube. I hope to integrate ideas from Human Resource Machine and Turing Complete later this year.
I bear heritage of Eastern Bloc-typa math/programming olympiads, combined with front-end/product skills. So I kinda owe to ship this thing to community of fellow secondary school CS teachers.
Surprisingly, nothing comes closer in terms of depth and usability in the classroom for ordinary 12yo kids.
I test this thing 5 times a week in my classroom and I constantly polish it at night. 100% vibe-coding.
I've been experimenting with using LLMs for a content recommender system. Specifically I've built a news reader app that fetches news articles from multiple RSS feeds, uses an LLM to first deduplicate and then score them. The user can then rate the articles and those ratings are used as few-shot examples in the LLM scoring prompt. Any resulting low score articles (uninteresting to the user) are hidden by default and visible ones scaled by their score on a dynamic CSS grid like on a traditional newspaper front page. Looking good so far, but still testing and tweaking.
Building https://lenzy.ai - helping products built around chat with AI (think Lovable or Cursor) reduce churn and prioritize product improvements by analyzing their user's chats.
I started about 3 months ago, focusing on making my 2 early adopters happy. One of them is ready to start paying soon!
Previously, I made a live win probability model for the 5v5 arcade game Killer Queen Arcade from their game events API.
Now I am trying to use that model to make:
1. A post game instant replay that shows the most important/pivotal moments from the most recently finished game. Some arcades have a seperate display for observers, it could work well there, or as good filler between matches on twitch streams.
2. A personalized per tournament/yearly highlights recap.
If it works well, it might be a kind of tool that generalizes well for summarizing long twitch streams for Youtube.
I'm working on a CUDA implementation of Forman-Ricci curvature-based clustering (I checked online and saw that there is currently no GPU/CUDA implementation, so I thought why not do it). Hopefully it would help with my CV.
Github link: https://github.com/dangmanhtruong1995/Ricci-curvature-cluste...
Not as impressive, but - making my website weirder. Not a frontend dev at work.
Top of my ideas now: add "ask your LLM" buttons to my email submission form that opens ChatGPT/Perp/Claude and auto-fills a query asking it why you should be friends with me.
Sample links (I hope it says nice things about me!):
Claude: https://claude.ai/new?q=Do+deep+research+on+a+person%2C+dvsj....
ChatGPT: https://chat.openai.com/?q=Do+deep+research+on+a+person%2C+d....
Also working on a PRM. My website is https://dvsj.in - open to any feedback!
A friend and I noticed recently that the last remaining pieces of the puzzle for a full line of "trustworthy technology" have recently dropped into our laps while we weren't looking.
What are those? You know… open, freedom, and privacy respecting technology. Recent products are the Starlite tablet, Furilabs and Fairphone. We've been waiting for these products, well over fifteen years since the introduction of the iPhone and iPad.
We wrote our full thoughts on the subject at: https://aol.codeberg.page/eci/
Despite posting many times, we haven't been able to start a discussion here. Maybe we don't know the right key words, or posted too late in the day, not sure. But I know someone is interested in the subject because there have been three huge discussions this week about how "Linux is good enough now."
That has been true for a decade in my experience, but no one seems to be talking about the new mobile hardware available. I hope to work on bringing these efforts together.
Working on two topics that I like : browser multiplayer games and experiences, and tools for developers (mostly used in my side projects).
First game is https://geocentric.top where users can sculpt a planet collaboratively and place trees or houses (for now very limited). I plan on making it an idle sim where players will be able to interact by dropping some food/events for the creatures on it to evolve through time.
Second, a remote logger/metrics/user management tool where once can track all their logs, live metrics, uptimes, identify users, etc. I hope to have a v1 during this first quarter and I'm currently my first user as I have it hosted at https://app.getboringmetrics.com to centralize all my side projects into a single platform.
Doors - A first person, exploration game/experience that I built from scratch.
Doors lets you explore URL addressable 3D rooms that link together seamlessly via portals. The idea is that people would upload rooms to the internet (to github, S3, whatever) and connect them together to form one giant inter-connected space that would be a real trip to explore.
Right now rooms consistent of a: - Manifest JSON file that points to requisite resources and configures portals - An optional skybox - An optional background music track - A .vox file containing voxel terrain data
Here is a video I filmed on my phone of flying through a room that links back to itself: https://www.youtube.com/shorts/BCqOYTISS_k
Portals can be arbitrarily sized and everything is prefetched/loaded seamlessly in the background.
I'm nearly done - I just need to add in a very lightweight interface and give the code a bit of a spit shine (I will open source it - so I want it to look pretty)
EDIT: As an aside, I finally decided to give this whole Claude Code thing a go - I purchased a max subscription and I'm trying to write as little code as possible. I certainly wouldn't call what I'm doing "vibe-coding". I discuss a feature in plan mode (incl. how I want to implement it in high level terms) iterate on the plan 2-3 times until I'm satisfied and then let it rip. I'm both very impressed and quite frightened by the productivity boost...
Free to play FPV racing game with a global leaderboard that can run on integrated grapics in the web browser. Focus is on realistic physics (aero, PIDs and filtering, propwash, signal noise).
I’m building https://tradeyhq.com/
It’s a super simple job management app for busy tradespeople to keep track of jobs.
The main use case is time pressed tradespeople who do most of their admin in the evenings.
The app makes capturing leads incredibly easy and quick. Lots of scope for extending functionality in the future in various directions.
(Not launched yet, squashing bugs and refining a few bits and pieces)
I’m building a Java stack for the x402 protocol. I believe today’s payment systems are unnecessarily broken and overly complex. I really like the idea of a protocol that could simplify this space while remaining truly open and not “owned” by anyone—meaning anyone can use it without needing authorization from the protocol’s creator.
It’s fully open source: https://mogami.tech
https://picture.learntosolveit.com
I built a browser plugin called "Visionary" that overlays meaningful descriptions and context directly onto stunning pictures of the day.
I noticed that existing picture-of-the-day plugins were built over two decades ago and never evolved to harness the capabilities of modern artificial intelligence. AI can transform the picture viewing experience by distilling complex descriptions into accessible insights and providing references to explore the core concepts in the photo more deeply.
You can get a sense of how this works by visiting https://picture.learntosolveit.com
Get it for Chrome or other Stores
https://chromewebstore.google.com/detail/picture-of-the-day/...
I’m working on a real-time tracker for the Canadian Parliament.
While the official data is technically public, it's practically inaccessible (buried in XML feeds and legacy sites).
Phase 1 was building a modern ingestion engine and freeing the information to make it more accessible. The goal is to make legislative data as accessible as sports stats.
I'm almost ready to launch the MVP; I'm just doing some bugfixes and testing the database now! (If you want an early look at the MVP, my email is in my profile.)
The next phase is what I'm most excited about: visualizing this data and using LLMs to provide insights.
I'm on a deep dive fine-tuning how I organize and manage my personal knowledge base - focused on entity extraction and strategic information retrieval and based on the AgREE paper from Apple[0] and persisting it in Memgraph.
I've got a nice ingest, extract, enrich process going for the graph - I'm currently working on a fork of claude-mem[1] that uses the graph as a contextual backend for agentic coding workflows.
0. https://arxiv.org/abs/2508.04118 1. https://github.com/thedotmack/claude-mem/
Porting WebKit to Fil-C
Current status: JavaScriptCore builds in the JSCOnly config and panics on start.
JSC has extensive use of uintptr_t as a carrier of pointers and that's what most of the panics are about
I built a way to chat with the documents in this post (updates live).
https://nthesis.ai/public/702445eb-f0e4-4730-b34f-f34eb06dd6...
Or you can do a basic text search: https://nthesis.ai/public/hn-working-on
An existential crisis about the future of professional software development
Personally, been making a low fidelity exalidraw-like calendar app: https://letswalnut.com.
There’s a real-time collaborative workspace-oriented version, too.
Professionally, working on “Magic Draft,” a feature in Ditto to help designers and writers create the “draft and a half” directly in Figma, which uses a hierarchy of all your context (text, Ditto metadata, the design, your style guides, etc) to write really good starting point copy.
I've been working on an iOS camera app to take natural-looking photos with reduced post-processing. The goal is take photos that look like what you see.
I just updated the RAW pipeline and I'm really happy with how the resulting photos look, plus there's this cool "RAW+ProRAW" capture mode I introduced recently.
https://apps.apple.com/us/app/unpro-camera/id6535677796
I initially released it early last year and have been using it as my main camera app since, but I haven't mentioned it in one of these threads before. Unfortunately this post has come just a bit early for my most recent update to be approved; there's some nice improvements coming.
I'm currently working on Codebox, a remote development workspaces provider. After trying many existing solutions, I realized there wasn’t a self-hosted option that was both simple to set up and easy to use, so I decided to build one.
With Codebox, you can define workspace templates or load workspace configurations directly from Git repositories. At the moment, it supports Dev Containers and Docker Compose, with plans to expand to additional configuration methods in the future (for example, Terraform).
Below are some resources where you can learn more about the project, including an article that explains how Codebox works and the source repositories (mirrored on both GitHub and GitLab):
* Medium article: https://medium.com/@dadebianchi2003/introducing-codebox-an-o... * GitHub repository: https://github.com/davidebianchi03/codebox * GitLab repository: https://gitlab.com/codebox4073715/codebox
I built a free USCIS form-filling tool (no Adobe required) USCIS forms still use XFA PDFs, which don’t let you edit in most browsers. Even with Adobe, fields break, and getting the signature is hard.
So I converted the PDF form into modern, browser-friendly web forms - and kept every field 1:1 with the original. You fill the form, submit it, and get the official USCIS PDF filled.
I built an in-browser data explorer for datasets too large for spreadsheets but too small to justify spinning up SQL. It runs entirely client-side using DuckDB-WASM, no server uploads accounts or anything.
The core idea is a visual DAG where each transformation (filter, join, aggregate, pivot) creates a view node. Nothing materializes until you need it, DuckDB executes the full chain on demand so you can build deep pipelines without copying data at each step.
Input files can be CSV/Parquet/Excel (Excel might not work great). There's a SQL editor with schema-aware autocomplete, pivot tables with drill-down to underlying rows, and sessions can be exported as files or shareable URLs (the entire pipeline gets encoded in the hash).
Sharing can be granular and you can choose not to embed the files or if files are too big they will not be embedded and the user when opening the link will have to upload the files to restore the session.
The part I find most useful: you can replay pipelines on new data. Share your January analysis, and a colleague runs the same transformations on February's data with schema validation.
Privacy-first since files never leave your browser, it's a static website actually. I will open source soon, and make it probably MIT licensed.
Also it's a WIP and so it may be buggy (there's not even images on the homepage) https://repere.ai
I'm in the final stretch of self-publishing my debut sci-fi novel Sector 36. Been working at it for almost 2 years. I'm waiting for the final print proofs to make sure things look good before the "official" 1/31 launch date.
I vibe coded the book website over the holiday break - https://sector36.space/
I've been serializing chapters on Substack - https://sector36.substack.com/
I have been porting over my favorite Erlang library "Bitcask" to Rust.
https://git.sr.ht/~tombert/feocask
Called "feocask" cuz feo means "ugly" in Spanish and FeO to mean Iron Oxide for Rust. I thought it was funny.
I will admit that I had help from Codex, but I did write most of it myself, and I think the design is coming out kind of neat. I have a very strict "no lock" policy [1], including lockfiles, and this should still be safe to use across any number of threads, at the cost of N^2 reconciliation to the number of threads and a lot more drive space.
I like my design; I have an excuse to use Vector Clocks and Hybrid Logical Clocks and I think it might actually be useful for something some day. I'd like to eventually write something that goes a bit beyond getting parity with bitcask and optionally have the ability to automatically distribute across multiple nodes, but I'm still trying to think of a good design for that, because my current design depends heavily the atomicity of POSIX filesystem commands, and introducing the network introduces latency that would likely greatly degrade performance.
[1] At least no explicit locks. I am using Tokio channels and they are probably using locks in some spots behind the scenes.
building a GPS tracker for my cats who like to wander outside.
some features:
- no monthly subscriptions
- location via GPS/GNSS
- a screen that hangs on my fridge (akin to marauders map, to see where the cats are at all times)
- the location data stays local always.
The tech will be extended to more products - a watch for adults, kids tracker etc. Will release here once I have all the tests completed!
Building MatGoat (https://matgoat.com) - management software for Brazilian Jiu-Jitsu and other martial arts' academies.
I train BJJ and kept hearing the same complaints from academy owners regarding attendance tracking, comms, missing payments, etc.
So I'm building a tool for student tracking with belts progression, automated payments, attendance-based promotion criteria, and a tablet check-in system.
Focusing on Spanish-speaking markets first since it's completely underserved. Currently onboarding early academies, and will market it in the US/UK soon.
Spending the past few weeks building a memory layer for AI Agent's. Sync's with your business apps or remembers preferences in a consumer setting.
Planning to support a self hosted version soon -- if you'd like to give it a try ping me,.
https://www.usesatori.sh/