2025-04-14 00:07:46
RT Geoffrey Litt
I've been hacking on a super simple AI assistant: built with a single SQLite table of memories and a handful of cron jobs, hosted on @ValDotTown.
The assistant is called Stevens. Every morning it sends a brief to me and my wife via Telegram, including our calendar schedules for the day, a preview of the weather forecast, any postal mail or packages we're expected to receive, and any reminders we've asked it to keep track of. All written up nice and formally, just like you'd expect from a proper butler!
Here's an example. (I'll use fake data throughout this post because our actual updates contain private information.)
Beyond the daily brief, we can communicate with Stevens on-demand—we can forward an email with some important info, or just leave a reminder or ask a question via Telegram chat.
That's Stevens. It's rudimentary, but already more useful to me than Siri!
Behind the scenes
Let's break down the simple architecture behind Stevens. The whole thing is hosted on @ValDotTown, a lovely platform that offers SQLite storage, HTTP request handling, scheduled cron jobs, and inbound/outbound email: a perfect set of capabilities for this project.
First, how does Stevens know what goes in the morning brief? The key is the butler's notebook, a log of everything that Stevens knows. There's an admin view where we can see the notebook contents—let's peek and see what's in there:
You can see some of the entries that fed into the morning brief above—for example, the parent-teacher conference has a log entry.
In addition to some arbitrary text, entries can have a *date* when they are expected to be relevant. There are also entries with no date that serve as general background info—you can see these particular background memories came from a Telegram chat, because Stevens does an intake interview via Telegram when you first get started.
With this notebook in hand, sending the morning brief is easy: just run a cron job which makes a call to the Claude API to write the update, and then sends the text to a Telegram thread. As context for the model, we include any log entries dated for the coming week, as well as the undated background entries.
Under the hood, the "notebook" is just a single SQLite table with a few columns.
But wait: how did the various log entries get there in the first place? In the admin view, we can watch Stevens buzzing around entering things into the log from various sources:
This is really just some data importers populating the table:
- An hourly data pull from the Google Calendar API
- An hourly check of the local weather forecast using a weather API
- I forward USPS Informed Delivery emails containing scans of our postal mail, and Stevens OCRs them using Claude
- Inbound Telegram and email messages can also result in log entries
- Every week, some "fun facts" get added into the log, as a way of adding some color to future daily updates.
This system is easily extensible with new importers. An importer is just any process that adds/edits memories in the log. The memory contents can be any arbitrary text, since they'll just be fed back into an LLM later anyways.
Reflections
A few quick reflections on this project:
It's very useful for personal AI tools to have access to broader context from other information sources. Awareness of things like my calendar and the weather forecast turns a dumb chatbot into a useful assistant. ChatGPT recently added memory of past conversations, but there's lots of information not stored within that silo. I've written before (https://x.com/geoffreylitt/status/1810442615264796864) about how the endgame for AI-driven personal software isn't more app silos, it's small tools operating on a shared pool of context about our lives.
"Memory" can start simple. In this case, the use cases of the assistant are limited, and its information is inherently time-bounded, so it's fairly easy to query for the relevant context to give to the LLM. It also helps that some modern models have long context windows. As the available information grows in size, RAG and fancier approaches to memory (https://x.com/sjwhitmore/status/1910439061615239520) may be needed, but you can start simple.
Vibe coding enables sillier projects. Initially, Stevens spoke with a dry tone, like you might expect from a generic Apple or Google product. But it turned out it was just more *fun* to have the assistant speak like a formal butler. This was trivial to do, just a couple lines in a prompt. Similarly, I decided to make the admin dashboard views feel like a video game, because why not? I generated the image assets in ChatGPT, and vibe coded the whole UI in Cursor + Claude 3.7 Sonnet; it took a tiny bit of extra effort in exchange for a lot more fun.
Try it yourself
Stevens isn't a product you can run out of the box, it's just a personal project I made for myself.
But if you're curious, you can check out the code here (https://www.val.town/x/geoffreylitt/stevensDemo).
If you want to explore, it's probably easier to just take this idea and run with it rather than using my code. You should be able to apply this basic pattern—a single memories table and an extensible constellation of cron jobs—to do lots of other useful things...
2025-04-13 04:22:23
tools for thought posts are back on HN frontpage. nature is healing
2025-04-12 12:52:49
something new.
2025-04-11 23:56:52
Pretty unique opportunity to work on something special
2025-04-11 11:39:12
This is a pretty incredible lineup, in particular for this topic of open source AI!
2025-04-11 04:20:32
RT Pol @ Fermat
We @fermat_app are hiring for a Barcelona or London-based account manager/customer success role for our Fashion & Luxury Vertical.
We are growing 30% MoM and serving some of the best brands in the world. If you want to join an AI startup making a very real impact in productivity, send me a DM or comment below.
If it's a fit, you can start working at Fermat next week.
