$ loading_
Give AI agents durable local memory, knowledge graph storage, and fast recall.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "server-memory" yet — see the docs or source repo.
Use server-memory to save the following user preferences and task history as searchable memory, and create entity relationships: The user prefers concise report style; completed a market research summary last week; is currently tracking the Q3 product launch plan.
Structured memory entries, entity links, and durable context that can be recalled later.
Use server-memory to search past memories related to the "Q3 product launch plan", summarize key events, related people, and open items, then generate a current status update.
A summary grounded in retrieved memories and a more coherent, accurate status update.
Use server-memory to organize the following into a knowledge graph with full-text search: Project Apollo is owned by product manager Lina, backend is developed by Chen, planned launch is in September, and the current risk is API performance bottlenecks.
A stored knowledge graph with entities, relationships, and full-text searchable records.
Store and query namespaced key-value memory for persistent agent context.
Persist conversational memory with SQLite and retrieve context using metadata.
Enable AI assistants to store, search, and manage persistent semantic memories.
Persistent knowledge-graph memory for MCP with semantic search and version tracking.
Provide long-term memory storage and fast semantic retrieval for AI applications.
Give AI clients persistent long-term memory with search and organization.