Zoe

So, here’s what I did on this last devlog before shipping:

1. (Forgot to mention it before) There’s also another system connected to the weather engine I developed, which is that every day at around 6AM it shares the weather of the day, combined from those 3 sources
2. Uploaded all n8n source code to GitHub
3. Finished pushing the web engine for Lana to GitHub too
4. Did a bunch of bug fixes
5. Added all the missing hackatime projects to this Flavortown project, I should have none left! Again, I can’t be more sorry that this happened, but internet went down for days and I went on a trip afterwards (end me pls :D)
6. Tried to do my best recording a demo video for this, bear in mind please that recording results of a research project is very very complicated.

Aaaand that’s pretty much it! I’ll ship now since the project will have its next “milestone”/research study release after Flavortown is supposed to end, and it would be quite dumb to keep it running before.
If you read the blog post on my website and find it interesting, please vote for this project! I want to get a new router to fix the internet issues I mentioned before and it’s expensive :pf: and it also gives me the energy to keep working :) Byeeee :333

So… I’ve been working offline for a while now because of outages on the network and a trip (as you can see by the lack of devlogs on my other projects too), but that didn’t mean I stopped working on this.
In that time I added an extra thing to Lana, being a human consciousness simulation engine.
It’s composed of 11 different n8n workflows, that together try to recreate consciousness in probably the most complex way it’s ever been done.
The system has REM, NREM and overall sleep simulation, has a world in which it has a body it can interact with, has a bunch of different tools, and also has a “job” (in this case being my assistant).
It has a custom made weather integration powered by 3 different weather APIs, has access to all my email accounts to let me know anything that happens through Slack, and finally the world simulation is also custom made, and can expand itself with new objects, people, places… as they’re discovered, while still being grounded in a real city (in this case Valencia Spain).
And idk if I can share much more things… You can check the source code for more info :3
I compressed my research over 15 days (which has not been logged as time, lol, but it’s been more than 60 hours) into a blog post on my website, which since it doesn’t fit here you can find at https://negrenavarro.me/blog/lana , and I’m now working on making a 90 days study and writing a research paper.

Oh and just FYI as I said 8h 3mins is nowhere near the amount I spent on this part of the project. Maybe I’m missing a hackatime project? I’ll check 😭

This means Lana is now a web UI, a helper Slack bot with tools, and a simulation of consciousness. Anyways hope you’ve enjoyed this project and how large it has become (probably one of the largest in terms of results in terms of Flavortown), and hope you vote it well :P 😭 even if it lacks lots of devlogs for this new consciousness part (I’ve spent 138,034,661 AI tokens on this which are kinda expensive as well :D).

The image attached to this devlog is a project structure graph made by me btw.

I can’t show all github commits since they use more than the max amount.

Anyways, wrote a blog post, added all missing projects to the projects section, and finally improved SEO and mobile mode.
Blog posts were not implemented before btw, so I made the whole rendering structure with MDX support, a little dot that follows your position on the page with coolio animations, and has pretty nice animations asw :333
Besides that added PostHog analytics since I was gifted their startup plan and wanted to add it to one of my projects.
Oh and sadly I couldn’t get Zoe naming to work so now it’s with my deadname end me :3
Anyways the project is kinda mostly done now that I finished the blog, I hope you like how it looks and the effort I spent in every little interaction! (Oh and if you can test on PC because all microinteractions and hovers are designed for it)

I’ve finally fixed all issues that made Vercel not build the site, so it’s finally accessible. Due to the #meta discussions, I’ve decided I’m going to take a break from working on this project more, at least for now, so at the very least I ask you guys to vote this project properly so my time at least didn’t go to waste. Again, want to note that this was going to be an HQ official project, and that at no point was it mentioned that it could be half disliked by the community.

Thanks for being here along the journey! :)

I’ve done a bunch of server side improvements on the Coolify server running this so that logging in with Educamos was easier and faster (I’ve been able to reduce login time from 15s to around 6-7s max on most of my tests), and also fixed an issue in which when you were logged in as a demo user you could not download attachments on demo content. This way reviewers can’t say it doesn’t work, finally :3

• log in as demo (0cb2c4c)
• demo responses (97da960)

idk how hackatime is tracking so little time lol today I’ve spent like 6h on this project anyways

You can now import data from Netflix (ratings and watch history) for it to be added onto the site. This also uses AI from HCAI as a fallback if it can’t properly match a show to its chapter and season (this took a lot lol).
I’ve also fixed a bunch of bugs like rotten tomatoes not showing for some series and directors also fetching music directors :P as well as other fisual errors.
I’ve also started working on a Seasons and Episodes section.

Profile pages!!!11!1! Now you can set a pfp, a name, description, etc… And I also went on dicebear to make a custom profile picture generator in the app itself :D

Movie info pages are here! They pull data from both TMDB and OMDB :D and yeah don’t know what else to say…
Oh yeah I made the dropdown in watchlist finally functional! So you can choose for each item whatever you need.

Started working on the UI for the platform itself, inspiring myself from Hardcover and other Book and Movie tracking sites. At the moment it supports TMDB data. You can also search for movies and shows.

I was planning on submitting this to scraps but all blots are gone and nothing in the shop is that cool for me sooo flavortown it is!
Anyways thank god the proj still isn’t finished.
Today I did the UI itself (which was the hardest, there’s micro animations everywhere I swear to god if someone says it’s AI like everyone seems to be saying everyone is using I’m imploding, AI can’t do these anims :/).
I also migrated texts from the old site to the new one, changed the colors and rewrote some details I thought didn’t look alright.
You can also see in the videos examples of the anims and details and content so far :) there’s still a bunch to do though.

Changelog

• readme! :)
• updated next version
• fixes
• fix smol bug
• email copy
• fix transition
• fix wording and tab bug
• content for the other projects
• first commit

I’m going to jump out of a window but the UI is starting to look better! I’m inspiring from Pi and Claude for this.

after like 23432432432 iterations I’ve got a login page I kinda like + simple logo, now I gotta finish the actual site UI

1. Added web search support
2. Started working on a web version of the app. This needs an almost full rework of the underlying arch, since the app is designed for a single user only and now multiple people can make an account and DM it. So far I’ve done the Appwrite setup and a basic implementetation, but I still need to remove all hardcoded stuff and make yaps and CDN not work with people that aren’t me. The UI is a sample one rn btw

1. Implemented Posthog logs for AI request so i can calculate token usage, compare models, etc.
2. Implemented Posthog logs for other project logs so I can have all logs in one place :D
   GitHub Commits so far:

• posthog :D (3451a2a)
• error and console logs on posthog (f0685f4)

ts was hard but I’ve implemented:

1. Reminders (the bot notifies me about something on a set date and time, and also reminds me every 30mins after it’s set to happen until I mark it as read)
2. New home tab (ss 1) with fixed tools (Slack doesn’t let me add more than 10 checkboxes apparently so now a multiselect)
3. Better notifications on bot startup that are now sent to my bot channel (this one also gets notifs from Coolify etc)

I got asked to add translations before the project was approved so uhhh english is here and that’s pretty much it for now :3 all demo data should now be translated and you can choose your language in settings. Note that you can’t change your language in demo mode, it’s now english only.

• readme yayyy (539b14c)
• I was asked to add translations so yay translations are here (3e75b52)

1. I’ve renamed the bot from “Zoe’s assistant angel” to Lana :D
2. I’ve moved all app tools to a subfolder, and made them fetch on bot startup so they’re separate from the code itself
3. I’ve added a settings db collection so I can enable/disable tools, change model and change prompt from the app’s Home tab. Models are fetched from the HC API btw

GitHub Commits so far:

• Lana name (9debd96)
• moved tools to subfolder (c3ae066)
• setings fetch from db (5bc4398)

1. I’ve changed the daily summary message to be much better, now being randomized and with hackatime stats.
2. I’ve started rewriting the README.

1. Fixed issues with her prompt making her act weird
2. Fixed her letting me know when she added stuff to memory
3. Added hackatime tool (love the «LAST_PROJECT» there to remind me of all time lost from config errors on projects)

1. I’ve fixed her replying to herself
2. I’ve fixed her content history and memory
3. I still don’t know why she reacts a bunch, it should be fixed but I can’t really test atm.

GitHub Commits so far:

• fixes on tools and context
• testing history changes
• test fix

1. I tried to implement coolify but it just went crazy (ss 1) so I decided to give up :3 and work a bit more on its personality.
2. Working on fixing it replying to itself (ss 2)
3. Working on making it agentic
4. Working on fixing too much reactions

1. Did prompt improvements to fix its interactions
2. Fixed an issue in which it sent 2413483432823 messages every time because message tool didn’t return success (help this was so hard to debug imma implode)
3. Fixed bugs on message sending on the main DM

GitHub Commits so far:

• added check to avoid sending messages twice, fixed bugs, better prompt
• silent tools fix, responses for tools are now sent in the correct thread
• prompt improvements
• silent tool, avoid saving existing items.
• prompt fix

Coolio changes:

1. Most tool calls are now async so replies happen asap and then notify you when done (or on error)
2. In case unauthorized users DM the bot, it refuses to reply XD
3. Some tools can now run in the moment instead of async
4. Threads!!! Now it doesn’t flood the chat and replies in a thread with your message (it can forward messages to chat though)
5. Reactions (it can now react to messages)

GitHub Commits so far:

• threads!1!!!11! reactions!!1111!! and yeah instant tools
• external user refusals, async tools

I’ve started to work on this! So far I’ve gotten AI replies to work, together with tool calls and embedding memory. Atm the prompt is very bad though for example, and the bot itself is nowhere close to what I want. The end objective is to have something like OpenClaw but that isn’t just a poorly done overhyped vibe coded weird app that doesn’t work and logs all your keys everywhere :/

GitHub Commits so far:

• less logs, better prompt
• model change
• removed part of checked debug logs
• started working on AI model

Medium update and release ready :DDDDD

1. Bought estudian.tech to host the app
2. Added demo mode (ss 2) In case you want to access the app please user user “demo” and password “demo”.
3. Combined all Microsoft 365 items into a single dropdown on the sidebar (ss 1)
4. Removed PII and hardcoded data and launched the repo
5. Changed the title on the sidebar from school name to welcome message (ss 3)

Added an Appwrite backend behind the app that stores the user’s profile picture and also implemented push notifications for event deadlines (also stored on the cloud).

Added profile popover on click and version news and changelog modal, and begun preparing the app for release by removing all embedded PII in it.

Educamos just decided that they wanted to change the entire Calendar UI (ss 1, kinda garbage in my opinion, also using like half of the page :skulk:), and since my app gets its data from there I’ve had to redo the entire backend for this endpoint. The way it works now is it loads the full week’s timetable and then parses the specific day, making everything faster and allowing me to cache the rest of the week to make less requests.

In addition, I’ve also done a few miscellaneous fixes such as adding icons to the login page for light and dark mode (ss 2), and fixing some content not appearing on the first auth.

The app also now logs you out when auth expires (lol) instead of just showing broken content and requiring you to go to settings and reauth.

Reversed the links to be able to insta log in to office and teams too, and added an option to set custom pfps.

Added calendar (ss 1)! You can now view your timetable for the week, as well as if you have any exams. Thankfully educamos returns JSON here.

Also made a logo weirdly inspired by books :) (img 2, haters would say it doesn’t look like a book :3)

Finally, I added “circulares” (ss 3, documents sent by the school) and “incidencias” (ss 4, issues related to you). These were previously just stubs in the sidebar. These work through HTML.

So yeah CDN has been down for a while… So this devlog is loooong :(( I promise I’ll go back to short devlogs right away (if stuff doesn’t break again :P) at least I’ll try to make this devlog as extense as possible.

Here’s what I’ve done atm:

1- Did a brief UI study on how Notion’s design works, and also made a moodboard

2- Made the UI for the homepage (ss 1) with sample data. I’m extremely proud of this design :)

3- Implemented “avisos” (notifications). This makes a request to Educamos’ API, reads the JSON it returns, and if necessary proxies the file it serves to be able to be downloaded on clients

4- Implemented “mis deberes y tareas” (tasks). Educamos decides that it wants to return an HTML instead of JSON, so I have to parse it and read it properly to be able to use it for my app

5- Birthdays. Educamos does return a JSON, so it’s as simple as analyzing that and proxying imgs

6- Notification counters (ss 2). Also JSON

7- “recent grades” info (ss 2). This fetches recent grades from Educamos (another HTML endpoint aaa) and parses it

8- Agenda. This gets the HTML from educamos, checks it’s for the correct day, finds any associated activities, and formats and shows it

9- Redirects for email and OneDrive (ss 3)

10- Grades and subjects page (ss 4 and 5). This was definitely the hardest part. When you ask Educamos for your subjects and grades, instead of returning a list of subjects with their grades as subitems, it returns ahuuge doc that I had to MANUALLY READ to find all associations between subjects and their grades. It contains them separate, with no linking between them by ID. Instead, you need to read every item, compare it against the list you have, guess if the item is a grade or a subject, and then analyze it

Help imma cry this has taken way too long but I won’t stop until it’s perfect and that’s all :) (pls vote this project well even if this is a big devlog it’s CDNs fault I’m losing my sanity aaaaaaa)

The points system is finished, + new logo!

The new logo is animated with lottie :yay: and designed by me on Figma :)
The points system lets you purchase items with points fully/partially or just pay with “real money” if you want.
Orders also now show points spent on them, and admins can refill users’ points in their UI too.
I also updated the order view to show costs, so now you can see how much you spent on things in an eaasier way, and how much shipping costed.
Finally, there’s a new redesigned checkout that uses 2 columns to show on the right all “money” stuff, and on the left all “data” you need to fill (at the moment shipping info).
There’s also a slider that lets you choose how many points you want to spend for the purchase.

Big new update! The shop now has:
a) An admin panel
b) Coupons support
c) Shipping info and costs support
d) Items being stored in DB instead of a JSON
e) Supercons (HC Icons) being used instead of custom SVG icons
f) “Checkout with HCB” (similar to credit refills but with predefined refill amounts and instant refreshes and payment)

This devlog is longer than usual because CDN went down :/ so I couldn’t make one earlier, but yeah… And we’re also working on a points system! Basically for each hour you work, you get around 5 points that you can spend instead of real money in the shop :yay: Sadly I can’t upload pics in this devlog since flavortown says 8 is the max :(

Added status updating through a Slack Bot! team members in #secret-channel :3 can approve/deny items, mark them as fulfilled, create and send refunds… as well as set custom messages for the user to see.

Recharging your account through HCB donations finally works as well!

Yay time wasn’t logged since browser but yeah had to spin up a custom instance of HCB to test all features and make sure we can actually make stuff work :P

Started to work on this! It’s starting to take shape… At the moment the homepage, browsing, adding to cart and logging in fully work! Don’t want to leek much…

I’ve also designed “drag to basket” and “sticker” mechanics (check attachments!)

I started with a rough demo and looking around original endpoints as a base inspiration to develop my own system using Appwrite. I first need to check and distinguish between server and client resources.

I’ve done a small “first iteration” of the LLM. Apparently I can choose from either overfitting or it not getting any training data :D

At the moment I’m working on adding more examples. Manually writing them is hard asf :/ I’m at 500 right now :D

Fixed errors and finally completed the condition support. Now you can also add a condition for calendar events existing and/or being in the next x minutes, so I also made a new Home Assistant dashboard to leverage this.

Successfully built on Appwrite pages with server-side rendering and implemented custom subdomain on my domain name (openink.isitzoe.dev).

Rebrand! Updated name. logos, description, README… Check out the new name, logo and banner! Designed in Figma :D

Conditions are here! You can now restrict screens to only show when certain conditions are true/false, and also override the other screens to make the screenshot with a condition the only one shown. Current conditions are “is x person in y zone” and “is it x day of the week”. You can also change start of week day, and the conditions refresh interval.

I really went TRMNL mode here, and made a whole web UI for the device. It allows users to create an account/log in, and get a device.json url together with a health url for their device. This way they can easily see if their device is online or not, change the screens (and their order), set “dev mode” (makes device.json be fetched every 2 minutes instead of every 15 minutes), and more. I also plan on adding conditions to the screens in order to show/hide them soon.

Made a new system that allows creating a device.json file hosted online to tell the display what to show and when. This way I can add screens that are shown every x minutes and cycle between each other, or set a screen to show during a specific time range.
This is making the project get closer to a full on TRMNL-like platform lol 🤣

Added some improvements in music assistant and the dashboard to support multiple sound outputs on the display. Now it has a list of sources and only shows the ones currently playing. There’s also a fake “Paused” source that only shows when no source is playing anything.

I created and printed a nice 3D design to be able to house the e-Ink display and my raspberry Pi, and also removed the borders around the items on the display to improve looks.

I made a simple version of the system. It uses JS to fetch my home assistant instance, load a specific dashboard, take a screenshot of it and then convert it to e-Ink format. Then, a python script takes that image and renders it on the display.
The Home Assistant dashboard uses custom e-Ink stylings to make everything look nice and clean, and shows my music status, pending tasks (synced from Notion) and the weather.

Finished the repo! It’s based around Upptime, but I had to modify pretty much every part of every repo for it to be able to work with my modifications. I completely redesigned how it looks, improved the READMEs, republished all packages… I must say, it looks fire!

Fixed events and added tickets for store bought event access passes.

Admin Panel is here! It allows admins to view and manage users, events, news and the store, together with some event settings.

Migrated everything from Notion DBs to Appwrite, and moved auth to HCA as well!