$ loading_
Provides persistent graph memory for LLMs with auto-linking and layered recall.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mem-graph" yet — see the docs or source repo.
Store the following user preferences, task history, and project context in mem-graph, and create entity relationships for future automatic recall: the user prefers concise replies; is building a recruiting assistant; and mainly uses Python, FastAPI, and PostgreSQL.
Returns stored memory nodes, relationship links, and a structured summary for future retrieval and recall.
Import these product research notes into mem-graph, use wikilinks and BM25 to automatically connect topics, competitors, and user pain points, and highlight highly related nodes.
Generates an interlinked knowledge graph with auto-linking results and highlighted key nodes.
Analyze activation across the current memory layers in mem-graph, and using spreading activation and synaptic decay, recommend which information should be reinforced, retained, or faded.
Outputs memory-layer analysis and recommendations to improve recall quality.
Provide persistent graph memory, semantic search, and traversal for AI agents.
Enable context-aware memory retrieval with authority weighting and conflict detection.
Persistent knowledge-graph memory for MCP with semantic search and version tracking.
Provide persistent graph-memory storage and retrieval for LLM agents via MCP.
Build and query persistent knowledge graphs so coding agents remember across sessions.
Give AI agents persistent knowledge-graph memory and cross-session retrieval.