Engram Cc

Name: Engram Cc
Author: Morous-Dev

by Morous-Devcommunityv0.1.4

Engram Context Continuum is a local memory substrate for AI coding assistants that maintains persistent context across sessions, folder renames, and tool switches.

From the registry: Universal AI coding assistant memory — session handoff, SLM compression, and semantic retrieval.

GitHub Repository

Install & configure

Prerequisites

required
Node.js >= 18
Requires Node.js 18 or later.
https://nodejs.org/
required
Run setup CLI
Run the setup CLI from your project root to create .engram-cc/ workspace, choose shared models dir, and generate assistant config snippets.
```
$ npx engram-cc
```

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `engram-cc` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Node.js >= 18** — Requires Node.js 18 or later. (https://nodejs.org/)
- **Run setup CLI** — Run the setup CLI from your project root to create .engram-cc/ workspace, choose shared models dir, and generate assistant config snippets. Run: `npx engram-cc`

Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["--yes","--package=@morous-dev/engram-cc","--","engramcc-mcp"]

Note: Local AI session memory substrate. 100% local, no API keys required. After npx engram-cc setup, generated project-local configs use node build/mcp/server.js instead. Canonical assistant-install command uses explicit --package form.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Local AI session memory substrate. 100% local, no API keys required. After npx engram-cc setup, generated project-local configs use node build/mcp/server.js instead. Canonical assistant-install command uses explicit --package form.