Neural Memory

Name: Neural Memory
Author: nhadaututtheky

by nhadaututthekycommunityv4.27.2

159

NeuralMemory is a tool that allows AI agents to store and recall memories using a graph-based approach, mimicking human brain functionality without relying on external databases or APIs.

From the registry: Persistent memory for AI agents — 55 MCP tools, spreading activation recall.

GitHub Repository

Install & configure

Prerequisites

required
Python 3.11+
Python 3.11 or higher
https://www.python.org/
required
Install neural-memory
pip install neural-memory
```
$ pip install neural-memory
```
required
Initialize
Run nmem init --full to set up the brain
```
$ nmem init --full
```

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `neural-memory` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Python 3.11+** — Python 3.11 or higher (https://www.python.org/)
- **Install neural-memory** — pip install neural-memory Run: `pip install neural-memory`
- **Initialize** — Run nmem init --full to set up the brain Run: `nmem init --full`

Canonical MCP server config (stdio transport):
- command: `nmem-mcp`
- args: []

Note: Local-first graph-based memory with spreading activation. No API calls, no vector DB. Free tier fully offline.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Local-first graph-based memory with spreading activation. No API calls, no vector DB. Free tier fully offline.