What is Engram Memory?

Engram Memory is a local-first cognitive memory engine specifically designed for AI agents. It provides robust tools for storing, retrieving, and managing agent memory, including advanced data structures and retrieval mechanisms.

How does Engram Memory ensure high-quality information retrieval?

Engram Memory utilizes a multi-stage hybrid retrieval pipeline that combines BM25 keyword search with vector similarity, adaptive RRF fusion, auto-PRF, and category boosting, achieving high recall rates for complex queries.

Can Engram Memory be easily integrated into existing AI agent systems?

Yes, it's exposed as an MCP server for seamless integration with clients like Claude Code or Copilot. It also provides a NuGet package for embedding the core engine directly into .NET applications, supporting JSON and SQLite backends.

Engram Memory

Name: Engram Memory
Author: wyckit

bywyckit

•

API 开发

开发者工具

数据科学与机器学习

Provides AI agents with a comprehensive, local-first cognitive memory engine featuring namespace-isolated vector storage, advanced retrieval mechanisms, and knowledge graph capabilities.

Engram Memory

bywyckit

•

API 开发

开发者工具

数据科学与机器学习

Provides AI agents with a comprehensive, local-first cognitive memory engine featuring namespace-isolated vector storage, advanced retrieval mechanisms, and knowledge graph capabilities.

Engram Memory serves as a powerful cognitive memory engine specifically designed for AI agents, operating as a local-first MCP server. It offers namespace-isolated vector storage, enabling LLMs to maintain distinct memory contexts. Its sophisticated retrieval system combines vector search with BM25 keyword matching, enhanced by features like synonym expansion and physics-based re-ranking to deliver high recall. Beyond simple storage, it includes a knowledge graph for semantic linking, intelligent clustering for organization, and lifecycle management with activation energy decay, allowing memories to evolve and fade based on relevance and usage. The engine also supports multi-agent sharing and hierarchical expert routing, making it a versatile and intelligent memory solution for complex AI systems.

主要功能

01Semantic clustering (DBSCAN) and multi-agent namespace sharing

02Namespace-isolated vector storage with Int8 scalar quantization

03Lifecycle management with activation energy decay and physics-based re-ranking

04Hybrid retrieval pipeline (BM25 + vector fusion, synonym expansion, cascade, auto-PRF)

05Knowledge graph with directed edges and BFS traversal

060 GitHub stars

使用案例

01Providing drop-in cognitive memory for any AI agent or LLM application

02Enhancing AI agents with advanced knowledge management, semantic retrieval, and memory lifecycle

03Enabling multi-agent systems with shared namespaces and hierarchical expert routing