{"slug": "memory-lantern-stories-that-stay", "title": "Memory Lantern — Stories That Stay 🏮", "summary": "A developer built Memory Lantern, a module within the Dr. T platform that uses a server-side Gemma 2 adapter (targeting local Ollama or an OpenAI-style hosted endpoint) to help families organize and revisit memories through a memory garden, timeline, storybook, editable AI-assisted narratives, printable pages, and archive export. The prompts constrain the model against impersonating deceased people or inventing biographical facts, and the developer reports 281 passing assertions across ten test suites, though live Gemma inference was reported as NOT_CONFIGURED during the audit and remains unverified. The guiding principle, the developer writes, is to \"preserve the memory, not impersonate the person.", "body_md": "What if AI could help us remember without pretending to be the people we miss?\n\nFor Hacktoberfest Week 4’s “Ghost in the Machine” theme, I chose a gentler interpretation of the ghost: not a digital imitation of someone who has passed away, but the traces people leave behind in their stories, voices, customs, and acts of love.\n\nEach memory becomes a lantern—a small light that can be revisited, organized, and shared intentionally.\n\nThe experience includes a memory garden, chronological timeline, storybook, editable AI-assisted narratives, printable remembrance pages, and archive export tools. Fictional sample memories make it possible to explore the experience without exposing anyone’s private family history.\n\nMy guiding principle is simple: preserve the memory, not impersonate the person.\n\nVideo:\n\nOpen the Memory Lantern tab in Dr. T.\n\nThe current environment has reported that the Gemma inference provider is not configured. The interface and integration are implemented, but live Gemma-generated stories should not be considered verified until the provider is configured and a real generation succeeds.\n\n**Platform repository:\n\n[https://github.com/Zenieverse/Dr.-T](https://github.com/Zenieverse/Dr.-T)\n\nMemory Lantern was developed as a new module within the existing Dr. T platform, with a standalone `memory-lantern/` package prepared for separation.\n\nThe implementation includes the memory domain types, UI components, memory service, server-side Gemma provider adapter, privacy documentation, and automated verification tests. The standalone package and its licensing and attribution should be checked before publication.\n\nMemory Lantern was built with TypeScript, React, the existing Dr. T application architecture, and a server-side AI provider adapter.\n\nThe open-weight AI integration targets Gemma 2, with support designed for local Ollama inference or a compatible hosted, OpenAI-style inference endpoint.\n\nThe intended workflow is straightforward:\n\nThe server-side prompt includes constraints against impersonating deceased people and inventing biographical facts. The interface is designed to distinguish user-supplied details from narrative enhancements.\n\nThe implementation also includes memory editing, search, timeline and storybook views, print-friendly reading, and export functionality. Existing Dr. T navigation and modules were preserved.\n\nThe supplied development audit reports successful TypeScript checking, a production build, and 281 passing assertions across ten test suites. Those figures still need to be reconciled with the individual suite totals before being presented as final verified results.\n\n**Important current limitation:** the hosted preview reported `NOT_CONFIGURED` for Gemma inference during the audit. Therefore, the integration is implemented, but successful live inference has not yet been established. I will update this section when a real Gemma generation has been verified.\n\nPersonal stories are too important to treat AI as a mysterious black box.\n\nOpen-weight models offer developers more choices about where inference runs, how a system is configured, and how its behavior can be evaluated. A local Gemma deployment can offer a different privacy trade-off from sending memories to a hosted provider, although local inference still requires appropriate device security and data handling.\n\nOpen innovation also makes it easier for others to inspect the architecture, reproduce the project, improve the safety constraints, and adapt the experience to different families, languages, and cultural traditions.\n\nFor Memory Lantern, the point is not to generate a convincing imitation of a person. It is to help people organize what they genuinely remember, while keeping the human in control of the story.\n\nA grandmother’s recipe is more than a list of ingredients. It might be the smell of tea in the kitchen, the way someone measured without a spoon, or the words they always said while serving it.\n\nMemory Lantern is for preserving those details without pretending that a machine can bring the person back.\n\nThe AI can help arrange the words. The memories, meaning, and final choices belong to the people who lived them.\n\nAdd only the partner prize categories for which the project meets the published eligibility requirements. Do not claim a category based solely on the presence of an integration; verify the rules and demonstrate the required functionality first.\n\nMemory Lantern is a new project developed within the Dr. T platform. Existing platform infrastructure and reused components should be credited clearly, alongside the licenses of any third-party libraries and model assets.", "url": "https://wpnews.pro/news/memory-lantern-stories-that-stay", "canonical_source": "https://dev.to/zenieverse/memory-lantern-stories-that-stay-n3k", "published_at": "2026-10-28 10:02:35+00:00", "updated_at": "2026-10-28 10:11:23.771304+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "generative-ai", "ai-ethics", "ai-tools"], "entities": ["Memory Lantern", "Dr. T", "Gemma 2", "Ollama", "Zenieverse", "Hacktoberfest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/memory-lantern-stories-that-stay", "markdown": "https://wpnews.pro/news/memory-lantern-stories-that-stay.md", "text": "https://wpnews.pro/news/memory-lantern-stories-that-stay.txt", "jsonld": "https://wpnews.pro/news/memory-lantern-stories-that-stay.jsonld"}}