mnemos is a new open-source tool that gives AI coding agents persistent, cloud-synced memory across sessions. Using hybrid vector and keyword search, mnemos allows coding agents to recall context from previous sessions, making long-running projects significantly more manageable.
The tool addresses one of the biggest limitations of AI coding assistants: the inability to remember what happened in previous conversations. With mnemos, agents can build up institutional knowledge about a codebase over time, remembering decisions, patterns, and context that would otherwise be lost.
The hybrid search approach combines semantic vector search with traditional keyword matching, ensuring that relevant memories surface regardless of how they were originally stored.