Back to directory

Open Memory Protocol (OMP)

A vendor-neutral specification, reference server and set of SDKs for AI tools to share portable memory about a user across different assistants, sessions and devices.

Open Memory Protocol (OMP)

Open Memory Protocol, or OMP, is a specification for how AI tools store, retrieve and share memory about a user and their context, aimed at the problem that each AI tool today remembers a user only within its own walls. Any tool that implements OMP can share memory with any other OMP-compatible tool.

The project is four things together: the specification itself, defining memory objects, a storage format and an HTTP API; a self-hostable, open-source reference server that runs in Docker with one command, or is available as a hosted instance; TypeScript and Python software development kits for building compatible tools; and adapters for Claude through MCP, OpenAI and Cursor, among others.

It requires Node.js 22 or newer to self-host, and includes a mobile-friendly progressive web app for browsing stored memories.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.