MemPalace/mempalace
MemPalace is an open-source, local-first AI memory system that stores and retrieves conversation history verbatim using semantic search, supporting pluggable backends like ChromaDB and integrating ...
Awesome MCP › Knowledge & Memory
CheMiguel23/MemoryMesh
MemoryMesh is a knowledge graph server designed to provide structured memory persistence for AI models, particularly optimized for text-based RPGs and interactive storytelling. It leverages the Model Context Protocol (MCP) to maintain consistent and dynamic memory across AI conversations, enabling richer and more immersive interactions. The project is based on the Knowledge Graph Memory Server from the MCP servers repository, retaining its core functionality while adding features tailored for gaming and narrative applications. The core concept of MemoryMesh revolves around using schemas to define the structure of data within the knowledge graph. These schemas specify node types, properties, relationships, and constraints, allowing the AI to generate, update, and delete nodes and edges automatically. Nodes represent entities or concepts such as characters, artifacts, or locations, while edges define relationships between these nodes, like ownership or location. MemoryMesh supports dynamic schema-based tools that are automatically generated from the schema definitions, simplifying interaction with the knowledge graph. This automation allows users to define complex data structures without manual coding of tools. The system also provides metadata to guide AI understanding and error feedback to improve AI interactions with the graph. The project includes a SchemaManager tool with a visual interface to facilitate schema creation and editing, making it accessible for users without deep technical knowledge. MemoryMesh comes with 11 pre-built schemas designed for text-based RPGs, offering a ready-to-use foundation for game developers. Additional features include an event system to track operations on the knowledge graph, relationship handling to encourage meaningful connections between data points, and support for metadata to enrich node descriptions. The server is implemented in TypeScript and is open-source under the MIT license. Overall, MemoryMesh is a powerful and flexible knowledge graph server that enhances AI memory capabilities for interactive storytelling and gaming, leveraging MCP to provide structured, persistent, and context-aware memory management.
https://github.com/CheMiguel23/MemoryMesh
Also in Knowledge & Memory
siyuan-note/siyuan
SiYuan is a privacy-first, self-hosted personal knowledge management system featuring block-level referencing, Markdown WYSIWYG editing, and support for the Model Context Protocol (MCP).
topoteretes/cognee
Cognee is an open-source project that provides scalable and modular memory capabilities for AI agents using ECL pipelines, enabling efficient management and retrieval of past interactions and diverse data types.
vectorize-io/hindsight
Hindsight is an agent memory system designed to create smarter, learning AI agents by moving beyond simple conversation history recall to encompass a biomimetic storage architecture for long-term m...
screenpipe/screenpipe
Screenpipe is a local-first, AI-powered memory tool that records computer activity (screen, audio, accessibility tree) to provide a searchable, automated context for personal AI agents and users, i...
Olow304/memvid
Memvid is a video-based AI memory library that stores millions of text chunks in MP4 files with ultra-fast semantic search, eliminating the need for traditional databases and enabling portable, efficient AI memory management.
EverMind-AI/EverOS
EverOS is an open-source Python framework for self-evolving, portable, long-term memory for AI agents, supporting multimodal ingestion and local-first persistence with Markdown as the source of truth.
MemTensor/MemOS
MemOS is a Memory Operating System for LLMs and AI agents that unifies long-term memory management, offering a single API for structured, multi-modal memory with enterprise-grade optimizations, sig...