Show HN: Memori – Dual-Mode Memory Layer for AI Agents
https://github.com/GibsonAI/memori
Hi Everyone,I’ve been working on an open-source project called Memori — it’s a memory layer for AI agents.
Memori is designed to give agents a persistent memory layer that supports both:
Short-term “conscious” memory (like working memory in humans)
Long-term retrieval using SQL full-text search (not vector stores)
It’s built around a multi-agent architecture (memory agent, conscious agent, retrieval agent), with structured storage and zero config to get started. It supports SQLite, Postgres, and MySQL.
Would love to hear what you think — all critique welcome. Happy to answer questions or hear if you’ve solved this differently.
(
2 comments
| on HN
)
Memori engin uses multiple agents to automatically identify and promote your most important long-term memories into short-term memory — so your AI can respond faster and with better context.
Let me know if you tested with AI Agent or the assistant with function calls?