FEGIS
Semantic tool-building framework and compiler leveraging the Model Context Protocol to transform YAML archetypes into schema-validated, reusable LLM interfaces with hybrid memory for persistent, semantically rich knowledge graph exploration.
Supercharge Your AI with FEGIS
Unlock the full potential of FEGIS through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.
Free tier available • No credit card required
API key for Qdrant if required
URL of the Qdrant vector database
http://localhost:6333Embedding model to use
nomic-ai/nomic-embed-text-v1.5Path to your FEGIS configuration YAML file
Name of the collection in Qdrant
fegisSecurity Notice
Your environment variables and credentials are securely stored and encrypted. LangDB never shares these configuration values with third parties.
Build and query real-time, temporally-aware knowledge graphs for AI agents with incremental updates, hybrid semantic and graph-based retrieval, and scalable, context-rich memory integration via the Model Context Protocol.
Added May 30, 2025
High-performance persistent memory system for the Model Context Protocol offering vector search, semantic search, knowledge graph management, and secure token-based authentication using libSQL for local and remote databases.
6 toolsAdded May 30, 2025
High-performance persistent memory system for the Model Context Protocol offering vector search, semantic search, knowledge graph management, and secure storage using libSQL for local and remote databases.
Added May 29, 2025
Persistent knowledge graph memory server enabling AI models with Model Context Protocol support to store, manage, and query user-related entities, relations, and observations across sessions for enhanced contextual understanding.
9 toolsAdded May 30, 2025
Memory Control Protocol (MCP) server leveraging Neo4j for advanced knowledge graph management, enabling creation, relation, and search of entities via a stdio interface for efficient model context integration.
Added May 30, 2025