$ loading_
Turn unstructured text into a searchable knowledge graph memory system.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "KG Memory" yet — see the docs or source repo.
Extract the following research notes into a knowledge graph using entity-relation-attribute structure. Use four entity types: person, organization, paper, and method, and output searchable structured results: {{research notes}}Structured knowledge graph output with entities, relations, attributes, and type constraints for later querying and tracking.
Extract projects, owners, decisions, risks, and dependencies from these meeting notes, store them in the knowledge graph memory, and organize a queryable relationship network by project: {{meeting notes}}A structured project knowledge network showing key entities and their relationships clearly.
Using this business ontology—customer, contract, product, order, and ticket—extract ontology-compliant entities and relations from the text and save them as searchable knowledge: {{business text}}Knowledge graph data aligned with the custom ontology, supporting precise search by entities and relations.
Give AI coding agents graph memory across sessions for knowledge retrieval.
Build a semantic graph from project files for search, knowledge, and task management.
Persistent knowledge-graph memory for MCP with semantic search and version tracking.
Build and query persistent knowledge graphs so coding agents remember across sessions.
Provides persistent graph memory for LLMs with auto-linking and layered recall.
Give LLMs persistent knowledge graph memory with semantic retrieval and contextual recall.