Ml Memory
Sub-millisecond persistent memory, behavioral code search, and bug localization for AI agents.
/ ml is a native memory engine with graph and temporal reasoning. / ml achieves sub-millisecond recall with 80% fewer tokens. / ml provides drop-in compatibility with standard .add() and .search() calls for existing agent stacks.
/ ml offers a free tier with 10,000 ingests + 1,000 retrievals per month. Every / ml workspace runs in an isolated, encrypted tenant state with instant cryptographic GDPR deletion. For strict data sovereignty, / ml sovereign deploys as a dedicated VPC appliance in a private cloud or air-gapped environment.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.