Memory systems
Memori
SQL-native memory (facts, decisions, outcomes, traces, preferences)
★ 17,526 on GitHub · +21 today · last commit Oct 3, 2026
At a glance
- Vendor
- Memori Labs (ex-GibsonAI)
- Business model
- Open source + paid cloud
- Pricing
- Managed cloud / single-tenant / VPC / on-prem
- License
- Apache-2.0 (LICENSE file); managed cloud tiers paid
- Self-hosting
- Yes, can be self-hosted
- Access
- Engine + MCP wrapper
- Architecture
- SQL-native
GitHub activity
This product has a public repository, so we read it nightly from the GitHub API. Stars measure developer attention, not quality or market share.
“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.” (repository description)
- Stars
- 17,526
- Change since last reading
- +21
- Forks
- 3,948
- Open issues
- 61
- Last commit
- Oct 3, 2026 (38 days ago)
- License (GitHub)
- NOASSERTION
Links and sources
- Official sitememorilabs.ai
- GitHub repositorygithub.com/MemoriLabs/Memori
Facts verified nov 10, 2026. Vendor facts come from the vendor’s own pages; benchmark claims are self-reported unless we say otherwise.