Recuerdos.local: An Offline Ofrenda & Memory Weaver

A developer built Recuerdos.local, a fully offline, voice-interactive digital ofrenda and memory archivist that interviews users about deceased loved ones, transcribes their stories with a local Whisper base.en-es model, and weaves them into a static digital remembrance. The system runs entirely on local hardware using open-source models, including a local Llama model for conversational prompting, and handles English-Spanish code-switching. During testing, the agent's follow-up question about a radio station prompted the developer's mother to recall a defunct 1980s Tejano station she had not thought of in years.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine https://dev.to/challenges/hacktoberfest-week4-2026-10-26 I built Recuerdos.local , a fully offline, voice-interactive digital ofrenda altar and memory archivist. It acts as a gentle conversational companion that interviews you about a lost loved one, transcribes your stories, and weaves them into a beautiful, static digital remembrance—extracting favorite foods, songs, and core memories along the way. The inspiration came from my family's Día de los Muertos traditions. We spend hours telling stories about those who have passed, but those oral histories fade. I wanted a way to preserve them without inviting corporate data-mining into our most intimate moments of grief and remembrance. Here is a terminal walkthrough of a session where I build an ofrenda for my grandfather: Since the project involves private family data, the live output generates locally on localhost:3000 and is not hosted publicly. Recuerdos.local is built entirely on open-source AI and runs strictly on local hardware. The open pieces are the only reason this project was possible: base.en-es model to capture and transcribe spoken family stories in real-time. It seamlessly handles code-switching between English and Spanish, which is crucial for my family. When building something that touches on death, memory, and family heritage, privacy is not just a feature; it is a fundamental sign of respect. You can see the evolution of the prompt engineering, the LangChain state management, and the local model configuration in my DevRelay session: The moment this project actually landed was during testing last weekend. I asked my mom to try it out by talking about her late father. She started telling a standard story about his old truck. The local Llama model picked up on a stray detail she mentioned about the radio and asked, "What station was usually playing on that radio?" She paused, teared up, and suddenly remembered the exact name of a defunct local Tejano radio station from the 1980s. She spent the next twenty minutes talking about the music they listened to. That detail would have been lost forever if the agent hadn't nudged her. Now, it's permanently etched into his digital ofrenda.