$ loading_
Adds persistent long-term memory with four-tier retrieval for AI assistants.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "supermem" yet — see the docs or source repo.
Please turn the user's preferences from this conversation into structured long-term memory and store them in supermem.
Returns a long-term preference summary and structured memory entries.
Please retrieve memory related to project budget and deadlines from supermem, organized chronologically.
Returns relevant historical memories and a timeline.
Please convert today's meeting conclusions into reusable long-term memory for the next session.
Returns reusable meeting conclusions and follow-up points.
When an AI assistant must stay consistent across many chats, it can store preferences, habits, and constraints as long-term memory. This avoids repeated explanations in later sessions.
Teams or individuals can preserve key project conclusions, decisions, and facts for later retrieval and reuse. It fits workflows that need structured memory.
When you need details mentioned earlier, layered retrieval can surface relevant memories from history. It works without a traditional RAG flow.
It is an MCP server that provides persistent AI memory. The description says it supports four-tier retrieval: SQLite FTS5, graph, vector, and an LLM agent.
The description explicitly says it works “without RAG.” It uses four-tier retrieval to provide structured, long-term memory instead of a traditional RAG workflow.
The provided material does not specify installation steps, keys, or runtime requirements; see the source repository.
Give AI assistants persistent memory with vector search, relationships, and access control.
Give AI agents persistent memory and semantic retrieval across conversations.
Persistent knowledge-graph memory for MCP with semantic search and version tracking.
Connect personal memory across LLMs for reusable context and knowledge recall.
Give AI assistants persistent memory, semantic search, and team collaboration.
Build and query persistent knowledge graphs so coding agents remember across sessions.