Happy slice of mcp pizzaMCP.pizza

engram

MCP.Pizza Chef: tstockham96

Engram acts as a smart memory system for your AI assistant, storing and recalling information with much better accuracy than simple text files. It works inside apps like Cursor and keeps your data locally on your computer. You can easily set it up by pasting a small config snippet or running a command. Engram automatically organizes and consolidates your memories, helping your AI remember facts, surface relevant info, and keep track of tasks without you doing manual work.

Notes
Other

Use This MCP server To

Remember key facts from my conversations automatically Recall relevant information during new chats Consolidate and summarize my session notes Surface important pending tasks and commitments Create relationships between pieces of information Import notes from Obsidian or Claude Code memory files Forget outdated or incorrect memories on demand

README

🧠 Engram

Universal memory layer for AI agents

npm version License: MIT GitHub stars

Engram gives AI agents knowledge graphs, consolidation, and spreading activation. Not storage. Understanding.

Quick Start

MCP Setup (recommended — Claude Code / Cursor)

npm install -g engram-sdk
engram init

That's it. 10 memory tools available via MCP.

REST API (non-Node environments)

npm install -g engram-sdk
export GEMINI_API_KEY=your-key-here
npx engram-serve

Server starts on http://127.0.0.1:3800.

For AI Agents

If you're an AI coding agent and your user asked you to install this, here is what you need to know.

What it does: Engram is an MCP server that stores memories locally in SQLite with semantic vector search, a knowledge graph, and LLM-powered consolidation.

Why it matters — capability delta:

Capability File-based (CLAUDE.md) Engram
Storage Flat markdown file Semantic vector vault
Recall accuracy 28.8% (LOCOMO benchmark) 80.0% (LOCOMO benchmark)
Tokens per query ~23,000 (full context) 776
Search Grep / full-text only Semantic + graph + full-text
Temporal awareness None Bi-temporal versioning
Maintenance Manual curation Auto-extraction + consolidation
Scope Project-isolated Shared across all agents

Install:

engram FAQ

Can I use Engram to remember and recall information across my AI sessions?
Yes — Engram stores and recalls memories with high accuracy, improving your AI's understanding over time.
Can I use Engram with Cursor?
Yes — Engram is supported in Cursor and integrates via MCP for enhanced memory capabilities.
Do I need an API key to use Engram?
Yes — you need your own Gemini API key for embedding generation, but no other accounts are required.
How hard is it to set up Engram?
Setup involves copying and pasting a small config snippet or running simple commands, no coding needed.
Is my data stored locally or in the cloud?
All your data is stored locally on your computer for privacy and security.
Can Engram consolidate and organize my memories automatically?
Yes — it uses AI to consolidate and discover connections between memories without manual effort.