BigHugger
GH Repository · 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.

stars
16,737
30-day movement
+17458/day
Related entries
60
Connections
1
python/uvmakedockeragent-appclaude-codememorystate-managementopenclawailong-short-term-memoryllmpythonagentmemory-managementPythonagent-memoryhermesstatefulragenterpriseai-memoryagenticaitypescript

Memori is an LLM-agnostic memory layer that converts agent execution and conversation into structured, persistent state. It is positioned for enterprise production systems, integrating with existing data infrastructure and supporting managed cloud, single-tenant cloud, VPC, and on-premises deployment.

You reach for it when your agents need durable, structured memory across sessions without replacing your current data stack.

Use it to

  • Persist agent conversation state across sessions
  • Structure agent execution history for production use
  • Deploy memory infrastructure on-prem or in a VPC
  • Give LLM-agnostic agents shared memory state
  • Add long- and short-term memory to agentic workflows

For Teams building production, enterprise-grade agentic applications

Role
agent-app
Language
Python
Licence
custom (licence file present)
Forks
3,464
Open issues
14
Last push
2026-09-03
Latest release
v1.0.0 · 2025-08-04
topicsagent-memorystate-managementllmenterprisepythonagenticai