File-based persistent memory for LLM assistants

Show HN: File-based persistent memory for LLM assistants

Based, File-based persistent memory for LLM assistants works in show hn launch.

Profile

I’ve been frustrated by how stateless most LLM assistants still are. Longer context windows and retrieval help with recall, but state usually disappears between sessions.I ended up building a file-based memory architecture where memory, rules, and state live explicitly outside the model. It’s modular (notes, OCR, training logs, etc.) and I’ve been using it daily for about three months as a general-purpose assistant. It doesn’t require fine-tuning or custom infrastructure — just files and an existing LLM backend.I’m curious how others here handle long-term state: files, databases, event sourcing, vector layers, or something else?For context: private, non-commercial use is free.http://metamemo

As a business in show hn launch, File-based persistent memory for LLM assistants is listed here with the public details available about it.

It is recorded at the Show HN launch stage.

Website: metamemoryworks.com