Engram MCP Server

by kael-bit Your server? Claim it

local only

Engram runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 2 Mar 2026.

Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion.

Installs per day peak 15 · avg 5 · -21% w/w

a month agotoday

Installs / week

npm · engram-rs-mcp

Stars

0 open issues

2 Mar 2026

Last commit

0 releases in 90 days

MIT

License

Rust

Nothing serious here today

Today is the operative word: we check Engram every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add engram -- npx -y engram-rs-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "engram": {
      "args": [
        "-y",
        "engram-rs-mcp"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.engram]
command = "npx"
args = ["-y", "engram-rs-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "engram": {
      "args": [
        "-y",
        "engram-rs-mcp"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "engram": {
      "args": [
        "-y",
        "engram-rs-mcp"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: ENGRAM_URL (URL of the engram server), ENGRAM_API_KEY (API key for authentication). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Engram

same job, measured the same way

Koda

by aabxtract

Verification and memory layer for coding-agent workflows.

48 installs/wk local only

Claudia

by yuvalsuede

Task management for AI agents with hierarchical tasks, dependencies, sprints, and coordination.

40 installs/wk local only

Instinct

by yakuphanycl

Self-learning memory for AI coding agents with pattern detection and confidence scoring.

6 installs/wk local only

Tacitus MCP Server

by ionasrobert

Long-term memory for AI agents: local-first PKM with provenance and hybrid search.

33 installs/wk local only

YourMemory

by sachitrafa

Persistent memory for AI agents. Memories decay with time and strengthen on recall.

439 installs/wk local only

Mnemex

by simplemindedbot

Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown).

64 installs/wk local only

Smara

by parallelromb

Persistent cross-platform memory for AI agents with Ebbinghaus decay scoring.

23 installs/wk local only

THOR

by nworks3d

Local memory for coding agents. A rule with a runnable proof can refuse a wrong command.

local only

Engram — questions

Answers built from our own checks of this server.

Why is there no uptime for Engram?

Engram runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package engram-rs-mcp was installed 35 times last week.

How do I connect Engram?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls engram-rs-mcp straight from npm; nothing to host, nothing to sign up for.

How many people use Engram?

The npm package engram-rs-mcp was installed 35 times in the last week. Week over week that is -21%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Engram open source?

Yes — it is published under the MIT licence, written in Rust and 27 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.