chemiguel23 avatar

MemoryMesh

chemiguel23/memorymesh

MemoryMesh is a knowledge graph server that enables AI models to maintain consistent, structured memory across conversations through schema-based tools and dynamic node management. It provides capabilities for defining custom data structures via schemas that automatically generate tools for adding, updating, and deleting knowledge graph nodes, with support for relationships and metadata to guide AI interactions. The server addresses the problem of maintaining coherent, persistent context in text-based RPGs and interactive storytelling applications where AI agents need to track complex, interconnected information about characters, settings, and narrative state.

GitHub stars
342
tools
11
last updated
Mar 10, 2026

Tools

11 tools

Public tool metadata for what this MCP can expose to an agent.

read_graphReturn the whole graph

Return the whole graph

No parameter schema in public metadata yet.

search_nodesFind nodes by name, type or metadata, with their direct neighbours

Find nodes by name, type or metadata, with their direct neighbours

No parameter schema in public metadata yet.

open_nodesReturn specific nodes by name, with their direct neighbours

Return specific nodes by name, with their direct neighbours

No parameter schema in public metadata yet.

add_nodesWork with nodes of any type

Work with nodes of any type

No parameter schema in public metadata yet.

update_nodesWork with nodes of any type

Work with nodes of any type

No parameter schema in public metadata yet.

delete_nodesWork with nodes of any type

Work with nodes of any type

No parameter schema in public metadata yet.

add_edgesWork with edges

Work with edges

No parameter schema in public metadata yet.

update_edgesWork with edges

Work with edges

No parameter schema in public metadata yet.

delete_edgesWork with edges

Work with edges

No parameter schema in public metadata yet.

add_metadataAdd or remove individual metadata entries

Add or remove individual metadata entries

No parameter schema in public metadata yet.

delete_metadataAdd or remove individual metadata entries

Add or remove individual metadata entries

No parameter schema in public metadata yet.

Sponsors

Readme

MemoryMesh

Release TypeScript License: MIT GitHub Stars

MemoryMesh is an MCP server that gives AI models a structured, long-term memory in the form of a knowledge graph. You describe the kinds of things you want to remember in small schema files (people, projects, characters, locations, books...), and MemoryMesh turns each one into tools the AI uses to add, update and delete that information, linking related items as it goes.

It works for anything you can describe as things and the connections between them: a text-based RPG world, the people and teams at your company, a personal CRM, or your reading notes.

Based on the Knowledge Graph Memory Server from the MCP servers repository.


View the full README on GitHub

Details

Repository
github.com/chemiguel23/memorymesh
Categories
AI & LLM Tools, Documents & Knowledge

Related AI & LLM Tools MCP servers

View all
1faviovazquez avatarshowtimefaviovazquez/showtimeLocal video studio for your coding agent: scenes, voice, music and captions, on your machine.321stars
2joenorton avatarComfyUIjoenorton/comfyui-mcp-serverA lightweight Python-based MCP server that interfaces with a local ComfyUI instance to generate images via AI agent requests.313stars
3guaardvark avatarGuaardvarkguaardvark/guaardvarkLocal AI studio on your GPU: images, video, music, voice, RAG. Needs the Guaardvark app installed.300stars
4harimxchoi avatarGoogle Surf Mcpharimxchoi/google-surf-mcpWeb, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.291stars
5s-stefanov avatarActual Budget MCP Servers-stefanov/actual-mcpMCP server exposing Actual Budget accounts, transactions, budgets and reporting to LLM assistants.279stars
6nirholas avatarthree.ws AgenCnirholas/three.wsBrowse the AgenC on-chain task marketplace, query the agent registry, and link identities.269stars