MemoriLabs/Memori
# Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
$ git clone https://github.com/MemoriLabs/Memori.git
stars
15,642
forks
2,868
language
Python
license
Other
What is MemoriLabs/Memori?
Memori provides a memory infrastructure layer for AI agents that persists conversation history and execution state in a structured, queryable format, independent of which LLM you're using. Developers use it to give agents reliable long-term memory and state management across sessions without replacing their existing data infrastructure. It supports deployment across cloud, VPC, and on-premises environments, making it suitable for production applications that need stateful agent behavior.
Links
Topics
Activity
26 open issues · last updated Jul 21, 2026