$ loading_
Give AI agents durable, encrypted, fully offline memory without cloud dependencies.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Compartment" MCP server from askskill: Run: claude mcp add 'io-github-maxfreedompollard-compartment' -- uvx compartment
When running an AI agent locally, developers can use it to preserve long-term context across sessions. It fits scenarios where the agent needs to remember preferences, project state, or task history.
Teams that are sensitive to data leaving their environment can use it to give agents memory without relying on the cloud. Its encrypted-at-rest and offline design suits environments that prioritize local control.
It is an MCP tool that provides durable memory for agents. The description indicates that it stores data persistently and keeps it encrypted at rest.
No. The provided description explicitly says it is fully offline, with no network, no API key, and no cloud dependency.
The provided material does not include installation or configuration steps. See the source repository for integration details.
Give AI coding agents persistent local shared memory across agents.
Give AI coding agents persistent memory across sessions for people, decisions, and context.
Give AI agents local-first persistent memory with namespace-scoped SQLite storage.
Give local-first AI agents persistent memory across tasks and sessions.
Provide AI agents with searchable long-term memory and conflict-aware recall.
Give AI agents persistent memory with semantic search and automatic memory management.