Engram is an open-source MCP server that acts as a universal memory layer for AI agents. It provides AI systems with advanced memory functions including semantic vector search, a knowledge graph, spreading activation for retrieval, LLM-powered consolidation, and bi-temporal versioning. Designed to integrate easily with agentic frameworks and tools, it replaces flat file or basic vector memory systems with an understanding-oriented, consolidated, and cross-project memory solution. All data is stored locally with the user's own LLM API key, offering privacy and no telemetry—ideal for developers, AI researchers, and autonomous agent builders seeking robust contextual memory for their systems.
Visit Engram's official website for product details and getting started.
Comprehensive guides and API documentation for integrating and utilizing Engram.
Explore example implementations and projects using Engram for practical insights.