MCPgee
MCPgee
MCPgeeMCPgee

Memora

v1.0.0•Knowledge & Memory•stable

Persistent memory with knowledge graph visualization, semantic/hybrid search, importance scoring, and cloud sync (S3/R2) for cross-session context management.

ai-agentclaudeknowledge-graphllmsmcp
Share:
406
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Memora?

Memora is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to persistent memory with knowledge graph visualization, semantic/hybrid search, importance scoring, and cloud sync (s3/r2) for cross-session context management.

Persistent memory with knowledge graph visualization, semantic/hybrid search, importance scoring, and cloud sync (S3/R2) for cross-session context management.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Persistent memory with knowledge graph visualization, semant

Use Cases

Maintain persistent cross-session context with semantic search and knowledge graphs.
Sync memory to cloud storage (S3/R2) for team collaboration.
agentic-box

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx memora

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Memora

Memora is a persistent memory MCP server that maintains a knowledge graph of facts, documents, tasks, and issues across AI sessions, with semantic and hybrid search, importance scoring, and optional cloud sync via Cloudflare D1, S3, or R2. It exposes a rich set of memory management tools including vector-based semantic search, AI-powered deduplication, typed relationship linking, and an interactive browser-based knowledge graph visualization. Developers and teams use Memora to give their AI assistants durable cross-session context — so Claude remembers project decisions, preferences, and ongoing tasks without needing to re-explain them each conversation.

Prerequisites

  • Python 3.10 or higher installed
  • pip or uv package manager
  • An OpenAI API key (for semantic embeddings and AI deduplication with the default configuration)
  • Claude Desktop or another MCP-compatible client
  • A Cloudflare account with D1 and R2 access (optional, for cloud sync only)
1

Install Memora from the GitHub repository

Install Memora directly from GitHub using pip. Add the [local] extra to include offline sentence-transformers embedding support (~2GB download), or omit it to use OpenAI embeddings instead.

# With OpenAI embeddings (lighter install)
pip install git+https://github.com/agentic-box/memora.git

# With local offline embeddings (~2GB)
pip install "memora[local] @ git+https://github.com/agentic-box/memora.git"
2

Configure Claude Desktop with local SQLite storage

Add Memora to your Claude Desktop MCP configuration using local SQLite storage. Set MEMORA_DB_PATH to your preferred database location and OPENAI_API_KEY for embeddings.

{
  "mcpServers": {
    "memora": {
      "command": "memora-server",
      "env": {
        "MEMORA_DB_PATH": "~/.local/share/memora/memories.db",
        "MEMORA_ALLOW_ANY_TAG": "1",
        "OPENAI_API_KEY": "sk-...",
        "MEMORA_EMBEDDING_MODEL": "openai"
      }
    }
  }
}
3

Enable the knowledge graph visualization (optional)

Start the server with the --graph-port flag to enable the interactive knowledge graph UI accessible at http://localhost:8765/graph. The graph updates in real time as memories are created.

memora-server --graph-port 8765
4

Configure cloud sync with Cloudflare D1 (optional)

For cross-device or team memory sharing, set up a Cloudflare D1 database and configure Memora to use it. Run the wrangler commands to create the database and apply the schema.

npx wrangler d1 create memora-graph
npx wrangler d1 execute memora-graph --file=memora-graph/schema.sql
5

Use Memora tools in your AI sessions

Once connected, Claude can call Memora's tools to store and retrieve persistent information. Key tools include memory_create, memory_semantic_search, memory_digest, memory_create_todo, and memory_insights.

Memora Examples

Client configuration

Configure Claude Desktop with Memora using local SQLite storage and OpenAI embeddings for semantic search.

{
  "mcpServers": {
    "memora": {
      "command": "memora-server",
      "env": {
        "MEMORA_DB_PATH": "~/.local/share/memora/memories.db",
        "MEMORA_ALLOW_ANY_TAG": "1",
        "OPENAI_API_KEY": "sk-...",
        "MEMORA_EMBEDDING_MODEL": "openai",
        "MEMORA_GRAPH_PORT": "8765"
      }
    }
  }
}

Prompts to try

Use these prompts to store, search, and organize persistent memories across sessions with Memora.

- "Remember that our API uses JWT authentication with a 24-hour expiry and store it as a project fact"
- "Search my memories for anything related to database migrations"
- "Create a todo: review the authentication module before Friday, priority high"
- "Show me a digest of everything you know about the payment integration project"
- "Find duplicate memories and merge any that are about the same topic"

Troubleshooting Memora

memora-server command not found after pip install

Ensure the pip install completed without errors and that the Python scripts directory is in your PATH. Try running `python -m memora` as an alternative, or check with `pip show memora` to find the install location and add its bin directory to PATH.

Semantic search returns irrelevant results or no results

Verify OPENAI_API_KEY is set correctly and the embeddings model is accessible. If using local embeddings (MEMORA_EMBEDDING_MODEL=sentence-transformers), the ~2GB model must finish downloading first. Run `memora-server --graph-port 8765` and check the visualization to confirm memories have embeddings.

Cloudflare D1 sync fails with authentication error

Ensure CLOUDFLARE_API_TOKEN is set with permissions for D1 read/write access. Verify the MEMORA_STORAGE_URI format is exactly `d1://<account-id>/<database-id>` and that the database was created and the schema applied with the wrangler commands.

Frequently Asked Questions about Memora

What is Memora?

Memora is a Model Context Protocol (MCP) server that persistent memory with knowledge graph visualization, semantic/hybrid search, importance scoring, and cloud sync (s3/r2) for cross-session context management. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Memora?

Follow the installation instructions on the Memora GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Memora?

Memora works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Memora free to use?

Yes, Memora is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Memora Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Memora? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "memora": { "command": "npx", "args": ["-y", "memora"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Memora?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides