MemoryKeeper: a local-first AI archive for preserving personal memories

Developer bdhamithkumara has built MemoryKeeper, an open-source archive for personal memories, submitted to the Hacktoberfest Open-Source AI Challenge. Users write a memory, and a locally run Gemma 3 4B model via Ollama suggests metadata such as people, places, dates, topics, themes, and a title. Every suggestion requires human review, and the original story is never rewritten by the AI. The app is built with Next.js, TypeScript, and Zod validation, and keeps all AI processing on the user's machine so private memories are not sent to a cloud service. The project includes 141 automated tests and was checked against the real local model.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)
Log in to join the discussion and vote.
Log in