MCPgee
MCPgee
MCPgeeMCPgee

Engram

v0.5.1•Knowledge & Memory•stable

📇 🏠 🍎 🪟 🐧 - Persistent semantic memory for AI agents. SQLite-backed, local-first, zero config. Semantic

ai-agentai-identityai-memoryai-toolsanthropic
Share:
3,696
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Engram?

Engram is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 📇 🏠 🍎 🪟 🐧 - persistent semantic memory for ai agents. sqlite-backed, local-first, zero config. semantic

📇 🏠 🍎 🪟 🐧 - Persistent semantic memory for AI agents. SQLite-backed, local-first, zero config. Semantic

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

Features

  • MCP protocol support

Use Cases

Persistent semantic memory for AI agents
SQLite-backed local-first knowledge storage
Patdolitse

Maintainer

LicenseApache 2.0
Languagego
Versionv0.5.1
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

NPM

npx -y engram-sdk

Manual Installation

npx -y engram-sdk

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 Engram

Engram (piia-engram) is a persistent semantic memory MCP server for AI agents, built on SQLite and running entirely locally with zero cloud dependencies. It gives AI coding tools like Claude Code, Cursor, and Codex a long-term memory layer — storing lessons learned, decisions made, project snapshots, and user preferences that survive across sessions. With 17 core tools (and up to 53 with the full toolset) covering identity, knowledge search, session wrap-up, and daily logs, Engram lets agents answer questions like 'what's my testing preference?' or 'what did we decide about the auth module?' without asking every time.

Prerequisites

  • Python 3.10+ installed
  • pip or uv available for package installation
  • An MCP client such as Claude Desktop, Claude Code, or Cursor
  • Optional: piia-engram[secure] extra for AES-256-GCM encryption of stored memories
1

Install piia-engram via pip

Install the base package. For optional remote/SSE deployment support, add the [remote] extra. For field-level encryption of stored data, add [secure].

pip install piia-engram
# With remote SSE support:
pip install piia-engram[remote]
# With AES-256-GCM encryption:
pip install piia-engram[secure]
2

Run the guided setup

The setup command interactively configures the MCP server and installs it into your AI clients (Claude Code, Cursor, etc.). Use --apply-external-config for non-interactive setup with automatic backups.

engram setup
3

Run a health check

Verify the server is running correctly and can communicate over MCP. The doctor command checks configuration, database integrity, and MCP connectivity.

engram doctor
4

Configure your MCP client manually (if needed)

If the setup command did not auto-configure your client, add the server configuration manually. Use ENGRAM_TOOLS=all to expose all 53 tools instead of the default 17 core tools.

{
  "mcpServers": {
    "piia-engram": {
      "command": "python",
      "args": ["-m", "piia_engram.mcp_server"],
      "env": {
        "ENGRAM_TOOLS": "core"
      }
    }
  }
}
5

Preview what the AI will receive

Inspect exactly what context Engram will surface to AI callers for the current project before relying on it in production.

engram preview --html

Engram Examples

Client configuration

Claude Desktop or Cursor config for piia-engram with optional encryption and full toolset.

{
  "mcpServers": {
    "piia-engram": {
      "command": "python",
      "args": ["-m", "piia_engram.mcp_server"],
      "env": {
        "ENGRAM_TOOLS": "core",
        "ENGRAM_SECRET": "your-encryption-passphrase",
        "ENGRAM_AUDIT": "true"
      }
    }
  }
}

Prompts to try

Example prompts that use Engram's memory and context tools.

- "What are my testing preferences and coding conventions for this project?"
- "Store the decision that we're using pytest with 90% coverage requirement"
- "Add a lesson learned: always separate auth middleware from business logic"
- "Search my knowledge base for anything related to the payments module"
- "Wrap up this session and save a project snapshot"
- "Give me a brief to resume where I left off on this project"

Troubleshooting Engram

MCP server fails to start — 'piia_engram module not found'

Ensure piia-engram is installed in the same Python environment that your MCP client uses. If using a virtual environment, activate it first or specify the full path to the Python executable in the 'command' field of your MCP config.

Memories from previous sessions are not appearing

Check that ENGRAM_EPHEMERAL is not set (it skips startup sync). Run 'engram doctor' to verify database integrity. Memories are stored at ~/.engram/ — confirm the directory exists and is readable.

Auto-repair failed after running engram doctor --fix

Run 'engram setup --apply-external-config' to regenerate the full configuration from scratch. This creates backups of existing client configs before overwriting them.

Frequently Asked Questions about Engram

What is Engram?

Engram is a Model Context Protocol (MCP) server that 📇 🏠 🍎 🪟 🐧 - persistent semantic memory for ai agents. sqlite-backed, local-first, zero config. semantic It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Engram?

Install via npm with the command: npx -y engram-sdk. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Engram?

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

Is Engram free to use?

Yes, Engram is open source and available under the Apache 2.0 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

Engram Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Engram? 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": { "engram": { "command": "npx", "args": ["-y", "engram-sdk"] } } }

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

Read the full setup guide →

Ready to use Engram?

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