Memory Nexus
OfficialFeatures automatic project detection by recognizing Git repositories and generating unique project hashes to ensure context and memories are correctly associated with specific codebases.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Memory Nexus for Claude Code
Persistent knowledge layer for Claude Code. Store context, retrieve briefings, and maintain continuity across sessions.
Installation
Create an account at memory-nexus.org
Generate an API key from your account dashboard
Set your API key as an environment variable:
export MEMORY_NEXUS_API_KEY="your-api-key-here"Add this plugin to Claude Code
Related MCP server: nexus-mcp
Features
Automatic Project Detection: Recognizes your git project and loads relevant context
Session Briefings: Get structured directives, objectives, and knowledge at session start
Semantic Search: Find memories by meaning, not keywords
Continuity: Switch between Claude, Codex, or any other platform while maintaining context
Multi-tier Subscriptions: Solo ($7/month), Crew ($49/month), Fleet ($199/month)
Available Commands
/memory-nexus status— Check account status and quota/memory-nexus search [query]— Search stored memories/memory-nexus forget [id]— Delete a memory/memory-nexus briefing— Get project briefing/memory-nexus account— Manage account and billing
How It Works
When you start a new Claude Code session:
Automatic Project Detection: The plugin detects your git repository and generates a unique project hash
Session Start Hook: Your project's stored context is retrieved from Memory Nexus
Briefing Injection: Directives (rules), objectives (intent), and knowledge (context) are automatically injected as additional context
Seamless Continuity: You can switch to another Claude instance or Codex, use the same API key, and get a coherent handoff without manual recap
Pricing
Tier | Cost | Features |
Solo | $7/month | 50 memories, 10 briefings/month, personal projects |
Crew | $49/month | 500 memories, 100 briefings/month, team projects |
Fleet | $199/month | 5000 memories, 1000 briefings/month, enterprise |
No free tier. No free trial.
Configuration
Set these environment variables:
MEMORY_NEXUS_API_KEY(required) — Your API key from the dashboardMEMORY_NEXUS_API_BASE(optional) — API endpoint, defaults tohttps://api.memory-nexus.org
Architecture
This plugin includes:
SessionStart Hook (
hooks/session_start_hook.sh) — Detects project, callssession_startendpoint, injects briefingMCP Server Bridge (
.mcp.json) — Connects to Memory Nexus Python MCP server for tool callsSkill Definition (
skills/memory-nexus/SKILL.md) — User-facing commands and documentationPlugin Metadata (
.claude-plugin/plugin.json) — Plugin registration with Claude Code
Troubleshooting
"No API key found"
Set
MEMORY_NEXUS_API_KEYenvironment variable and restart Claude Code
"Project hash not detected"
Make sure you're working in a git repository
The hook will silently skip if not in a git project
"Briefing is empty"
This is the first session for your project. Start storing memories with
/memory-nexuscommands.The briefing will grow as you add context.
Learn More
Visit memory-nexus.org for the full documentation.
This server cannot be deployed
Maintenance
Related MCP Connectors
shared AI-context layer for teams — persistent memory your agents search and update over MCP
An MCP memory server. One memory your agents share — across models, devices and apps.
Cross-tool persistent memory and context for AI assistants over MCP.
Persistent memory for AI agents to retain, retrieve, and recall conversation context through MCP.
Related MCP Servers
- AlicenseBqualityAmaintenanceNexus Memory gives every MCP-compatible agent one persistent, self-hosted shared memory with hybrid retrieval, drift detection, and anti-poisoning features.193MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that wraps the nexus CLI, giving AI agents cross-session memory, semantic search, preference learning, and smart context injection.131 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to share persistent memory by capturing, classifying, synthesizing, and retrieving knowledge from sources like Obsidian, code, and transcripts via MCP and REST APIs. Provides token-optimized search, three-tier memory, and self-learning capture of sessions and fixes so multiple agents can build on prior context.5 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to share a persistent, self-improving memory by ingesting sources such as Obsidian vaults, code, transcripts, and bookmarks, then classifying, promoting, synthesizing, and retrieving that knowledge through token-optimized search across MCP and REST interfaces. Agents can capture sessions and fixes so context compounds across sessions and across Claude, Codex, Gemini, and any other MCP client.5 npmMIT