MOM (Memory Oriented Machine) is an open-source, on-premises memory layer for AI agents. It captures and retrieves persistent context across sessions, ensuring data stays within the user's infrastructure. Designed for developers and enterprises needing secure, persistent agent memory.
In the Frameworks & SDKs space, MOM takes a focused approach. It focuses on allowing AI agents to retain and retrieve persistent memory across sessions while ensuring data residency and privacy. MOM is an open-source project aimed at AI agent developers and enterprise teams. The project is open source (Apache-2.0). It runs on the command line, macOS, and Linux, and it can be self-hosted.
Behind MOM is momhq, and the product first shipped in 2026. The project is developed in the open on GitHub with 57 stars and 503 commits in the last 90 days. Across PulseGate's embedding index, MOM has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are persistent memory, on-premises storage, and session context capture.
Latest indexed changes and source events
Other apps tracked under the same category.
