Memori
Memori gives production agent systems a model-agnostic memory layer that turns executions and conversations into persistent structured state. 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.
Pricing
Open source (free)
Update history
Last updated 2026-10-03;Listed 2026-11-05
Author
MemoriLabs
Trust info
Listed on 2026-11-05; Last updated 2026-10-03; Data synced on 2026-11-21
Trial feedback
Like it? Vote to help it rank higher.
From the README
Memori was evaluated on the LoCoMo benchmark for long-conversation memory and achieved 87% overall accuracy while using an average of 721 tokens per query. That is just 2.8% of the full-context footprint, showing that structured memory can preserve reasoning quality without forcing large prompts int…
- Stars
- ★ 17.6k
- Category rank
- #303
- Language
- Python
- License
- Not specified
- Last updated
- 2026-10-03
- Category
- AI assistants & agents
- Section
- General





