Keepsake: an offline memory companion I built for my grandmother

·7 views

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend I built Keepsake for my grandmother — Dadi. It is a private, offline AI companion that becomes her long-term memory. We feed it her stories, recipes, routines, and the people in her life. It remembers them in Tiger Data (Postgres + pgvector + full-text + Timescale), talks through Gemma 3 running locally via Ollama, and gets a little more like her every time we chat — because every conversation is written back into the archive. It does not have to be huge.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Vertical Slices: Rethinking Software Architecture

“Your architecture should scream what the system does.” — Martin Fowler On September 26, 2026, I participated one of the best technology events we have here in São Paulo: MVP Conf. Being surrounded by so many technically exceptional people was one of the best experiences I could have for my career. Among the various talks I attended, a few particularly caught my attention: Event Sourcing in production: implementing Aggregates and Event Store with C# and EF Core — Antônio Falcão Jr. Ports, Adapters & Vertical Slices — William Santos Both talked about a relatively new trend in software architect

0 comments Read more at DEV Community

ProgrammingDEV Community ·

CodeBuddy — An AI Coding Mentor That Learns From Your Mistakes

What I Built I built CodeBuddy, a local-first AI coding mentor for a friend who is learning programming and DSA. My friend often gets stuck while debugging code and usually has to ask someone else for help. The problem isn't always finding the correct solution — it's understanding why the code is wrong and how to avoid making the same mistake again. CodeBuddy lets them paste their code, select the programming language, and provide an error or describe the expected behavior. Instead of immediately giving them the answer, it guides them through the problem using progressive hints and explanation

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Long-Horizon Agents: Why Multi-Turn Reasoning Breaks and the Practical Training Tricks That Fix It

Almost every modern language model looks impressive on a two-step demo. You ask it to check a database or summarize a document, it calls the right tool, formats the answer, and looks like an autonomous engineer. The illusion falls apart the moment you ask that same model to complete a 30- or 50-step workflow: diagnosing a failing Kubernetes cluster, navigating a multi-file pull request, or running a 48-hour industrial simulation. Around step 10, the agent makes a small typo in a terminal command. By step 15, it misinterprets a confusing error message.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

[Boost]

I Built StudyBuddy AI for a Friend Who Was Tired of Turning Notes Into Study Material 📚🤖 Hacktoberfest Weekend Challenge: Build for a Friend Submission 🤝 Jainil Chavda Oct 3 #weekendchallenge #hf26challenge #devchallenge #ai 1 reaction Add Comment 5 min read

0 comments Read more at DEV Community