Published March 14, 2026 | Version v3
Working paper Open

Building Persistent AI Systems Without a Traditional Database

Description

This paper shows a new way to build AI assistants without using a complex database. Instead of hiding data in a database, we store the AI’s memory, personality, and skills in simple Markdown files that anyone can read. For systems like personal assistants or those with fewer users, a heavy database is often overkill.

Proper Segregation of markdown files:

  1. working_memory.md
  2. episodic_memory.md
  3. semantic_memory.md
  4. personality.md
  5. habits.md
  6. self_reflection.md
  7. skills.md
  8. skill_context.md

To help the AI find information quickly, we use a tool called FAISS to search through these files, but the files themselves always remain the main source of truth.

By using simple files instead of a database, the system is much easier to fix, track, and move. It’s a perfect 'middle ground' for personal AI projects because it’s simple to manage but still powerful enough to handle complex tasks.

Files

Markdown_Native_Architecture.pdf

Files (37.4 kB)

Name Size Download all
md5:dd9ccf7678a3b8dd79450f635ae1d71e
37.4 kB Preview Download

Additional details

Dates

Available
2026-03-14

Software

Repository URL
https://github.com/maluskarhrishikesh-afk/OctaMind
Programming language
Python
Development Status
Active