Happy slice of mcp pizzaMCP.pizza

engram-rs

MCP.Pizza Chef: kael-bit

Engram-rs lets your AI assistant remember important information while automatically forgetting less relevant details. It organizes memories into topics and promotes key knowledge for long-term use. Compatible with apps like Cursor and Windsurf, it runs as a standalone server you set up with developer tools. This makes your AI’s memory smarter, more focused, and easier to browse without manual tagging or clutter.

Other

Use This MCP server To

Keep my AI’s memory focused on important decisions and lessons Automatically organize AI knowledge into topic clusters Recall past instructions or preferences quickly Forget outdated or irrelevant information over time Restore full AI context after a break Tag memories to trigger specific actions Merge duplicate memories into one coherent note

README

engram-rs

CI License: MIT Rust GitHub stars Docker

Memory engine for AI agents. Two axes: time (three-layer decay & promotion) and space (self-organizing topic tree). Important memories get promoted, noise fades, related knowledge clusters automatically.

Most agent memory is a flat store — dump everything in, keyword search to get it back. No forgetting, no organization, no lifecycle. engram-rs adds the part that makes memory actually useful: the ability to forget what doesn't matter and surface what does.

engram demo — store, context reset, recall

Single Rust binary, one SQLite file, zero external dependencies. No Python, no Redis, no vector DB — curl | bash and it runs. ~10 MB binary, ~100 MB RSS, single-digit ms search latency.

Quick Start

# Install (interactive — will prompt for embedding provider config)
curl -fsSL https://raw.githubusercontent.com/kael-bit/engram-rs/main/install.sh | bash

# Store a memory
curl -X POST http://localhost:3917/memories \
  -d '{"content": "Always run tests before deploying", "tags": ["deploy"]}'

# Recall by meaning
curl -X POST http://localhost:3917/recall \
  -d '{"query": "deployment checklist"}'

# Restore full context (session start)
curl http://localhost:3917/resume

What It Does

engram-rs FAQ

Can I use this to help my AI remember important information and forget less relevant details?
Yes — engram-rs manages memories by importance, promoting key info and fading noise, making AI memory more useful.
Can I use this to organize my AI's knowledge by topics automatically?
Yes — it groups related memories into a self-organizing topic tree for easy browsing.
Which AI apps support engram-rs?
It works with Cursor and Windsurf, among others that support MCP servers.
Do I need an API key or account to use engram-rs?
No — it runs as a standalone server with zero external dependencies.
How hard is it to set up engram-rs?
Setup requires developer skills like running Docker or command-line installs; it’s not one-click.
Does engram-rs require extra software like Python or databases?
No — it’s a single Rust binary with a built-in database, so no extra software needed.