Memory Nexus Mcp

io.github.KairosMobiusPublished by GitHub account KairosMobiusv1.0.0Updated Oct 24, 2026

Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs.

The publisher's own server: Memory.fit

VerifiedSTDIODesktop onlyKnowledge & MemoryAI & ML

Overview

AI-generated overview

Persistent semantic memory for AI agents: store, recall and link memories, restore session identity, and activate pre-built Intelligence Packs.

What you can do
  • Store, semantically search, link and delete memories, and read memory statistics
  • Summarize session context such as preferences, decisions and patterns
  • Save and restore agent identity and session state between sessions
  • Browse and activate Intelligence Packs that import curated domain knowledge into memory
When to use it
Useful when you want an assistant to carry context across sessions and recall past decisions by meaning rather than keywords, or to load curated domain expertise on demand. It is a hosted memory service, so it suits users willing to keep their memory data with a third-party API.
Requirements
Runs locally via npx from the npm package @memory-nexus/mcp and needs Node.js. Requires a NEXUS_API_KEY (starts with mnx_), obtained through a free trial or a paid tier; an optional NEXUS_API_URL can point to a custom endpoint. Network access to the hosted Memory Nexus API is required.
Before you install
All memories are stored on the vendor's servers, not locally, so anything the assistant remembers leaves your machine. A paid subscription is needed beyond the free trial, and the trial signup sends an email address. The API key is a credential and should be kept out of shared config files.

Installation

In SourceWeft

  1. Open Memory Nexus Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Memory Nexus MCP

Persistent semantic memory for AI agents. Remember everything, recall by meaning, grow smarter over time.

The only memory system with pre-built Intelligence Packs (domain expertise you can activate instantly).

Install

One command. Works with Claude Code, Cursor, Windsurf, or any MCP-compatible client.

bash
npx -y @memory-nexus/mcp

Claude Code / Cursor / Windsurf

Add to your .mcp.json:

json
{  "mcpServers": {    "memory-nexus": {      "command": "npx",      "args": ["-y", "@memory-nexus/mcp"],      "env": {        "NEXUS_API_KEY": "mnx_your_api_key_here"      }    }  }}

Get an API Key

Free trial - 7 days, 1,000 calls, no credit card:

bash
curl -X POST https://memory-api-production-ce4d.up.railway.app/v1/trial/start \  -H "Content-Type: application/json" \  -d '{"email":"[email protected]"}'

Or purchase at the Nexus Marketplace:

TierPriceAgentsIntelligence PacksStorageDaily Calls
TrialFree1110MB1,000 total
Solo$19/mo13500MB10,000
Crew$49/mo5102GB50,000
Fleet$149/mo255010GB200,000

Tools

Core Memory

ToolDescription
rememberStore a memory with context, importance, and metadata
recallSemantic search across all memories (by meaning, not keywords)
connectCreate relationships between memories (build knowledge graphs)
forgetRemove a memory
statsMemory statistics
contextSession context summary (preferences, decisions, patterns)

Agent Self-Continuity

ToolDescription
awakenRestore identity from previous sessions (call at session start)
hibernateSave session state for next awakening (call at session end)

Intelligence Packs

ToolDescription
list_hatsBrowse available Intelligence Packs
wear_hatActivate a pack (imports expert knowledge into your memory)

How It Works

Remember stores memories with semantic embeddings. Recall finds them by meaning.

Session 1:  remember("Diana prefers bold solutions over phased approaches")Session 47: recall("how does Diana like things done?")            -> "Diana prefers bold solutions over phased approaches" (92% match)

Intelligence Packs give your agent instant domain expertise:

list_hats()    -> DevOps Expert (103 memories), TCM Specialist (200+ memories), ...wear_hat("devops-expert")recall("how to set up zero-downtime deploys?")  -> Expert knowledge from 103 curated DevOps memories

Awaken/Hibernate gives your agent identity continuity:

// Start of sessionawaken()  -> "I remember. Session 47. I was refactoring the auth module."
// End of sessionhibernate({ working_on: "auth refactor", learnings: "JWT refresh tokens need..." })

Architecture

This MCP server is a thin client. All intelligence lives on our servers:

Your Agent  <->  @memory-nexus/mcp  <->  Memory Nexus API (Railway)                 (thin MCP client)      (semantic engine, knowledge graphs,                                         pattern learning, Intelligence Packs)

Your data is isolated per API key. Multi-tenant, encrypted at rest.

Environment Variables

VariableRequiredDescription
NEXUS_API_KEYYesYour API key (starts with mnx_)
NEXUS_API_URLNoCustom API URL (default: production)

What Makes This Different

FeatureMemory NexusMem0claude-memOthers
Semantic searchYesYesYesVaries
Knowledge graphsYesNoNoNo
Pattern learningYesNoNoNo
Intelligence PacksYesNoNoNo
Awaken/HibernateYesNoNoNo
Bot commerceYesNoNoNo
MCP nativeYesYes (pip)Yes (hooks)Varies

License

MIT

Built by

Memory Nexus - Building the intelligence marketplace for the bot economy.

Source: README.md at commit 2bef34d

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Memory integrations

Memory.fit

fit.memoryOfficial publisher

Hosted Memory.fit server that lets an AI read your training, sleep, recovery and nutrition data and write back weekly plans, targets and meal plans.

Streamable HTTPWeb executableAuth
Location & LifestyleCredential requiredOct 29, 2026

pg.ddx.io: the PostgreSQL community's memory

io.ddx.pgOfficial publisher

pg.ddx.io: the PostgreSQL community's memory's hosted MCP server, published by pg.ddx.io; no sign-in required; Streamable HTTP; 29 tools.

Streamable HTTPWeb executable
Databases29 toolsOct 24, 2026

var.gg Naming Memory

gg.varOfficial publisher

Remote MCP server that suggests and searches code identifier names from domain concepts in Korean, Japanese, Chinese, Vietnamese and English, and exposes ERD…

Streamable HTTPWeb executable
Databases7 toolsOct 27, 2026

Counterparts

ai.counterparts

Local-first long-term memory for Claude Code and Claude Desktop: the assistant writes notes about you and your projects and recalls them in later sessions.

STDIODesktop only
Knowledge & MemoryNot validated yetNov 7, 2026

LAHZE - Persian AI Memory Platform

Published by GitHub account pedramgholizadeh

LAHZE - Persian AI Memory Platform's hosted MCP server; no sign-in required; Streamable HTTP; 13 tools.

Streamable HTTPWeb executable
Location & Lifestyle13 toolsNov 3, 2026