What it does
The server provides long-term memory for AI agents, storing three kinds of information: semantic facts, episodic events and procedural workflows. The publisher describes it as memory that persists beyond a single session, so an agent can draw on earlier information when it runs again.
It would be reached for when an agent needs to retain and recall facts, past events or repeatable workflows across conversations, rather than starting from nothing each time. Its development and productivity tags point to use in agent-building and everyday agent workflows.
The server is an MCP server, so it is connected to an MCP-compatible client and its tools become available to the agent. The publisher's source repository is hosted on GitHub.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.alibaizhanov/mengram
Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows
v2.25.4As shown on registry.modelcontextprotocol.io when we last read it