cortex-memory

Cortex Memory

Persistent memory engine for AI agents. Knowledge survives across sessions — recall what you learned last week, track evolving beliefs, detect contradictions, and build a knowledge graph over time.

Source: github.com/Fozikio/cortex-engine (MIT) | npm

Prerequisites

This skill requires cortex-engine running as an MCP server. Install it separately before using this skill:

npm install -g @fozikio/cortex-engine

Install the scoped package, unpinned. The unscoped cortex-engine on npm is the old name and is deprecated — but old versions of it still resolve, so pinning one installs an ancient engine that works just well enough to hide the problem. Always use @fozikio/cortex-engine, and let it take the latest.

Then initialize and start:

fozikio init my-agent    # scaffold a workspace
fozikio up               # start ollama + nli, wait until they answer
fozikio serve            # start the MCP server (stdio)

If anything goes wrong, fozikio doctor diagnoses the install and tells you how to fix it.

Runs locally with SQLite + Ollama. No cloud accounts needed. The skill instructions below are read-only — they teach your agent how to use cortex tools, they don't execute anything.

Managing the services

cortex-engine 1.4.0+ ships a service supervisor, so you do not have to babysit Ollama:

Command	What it does
fozikio up	start every service and wait until it actually answers
fozikio status	service health (HTTP probe, not PID liveness); exits 1 if unhealthy
fozikio doctor	diagnose the install and say how to fix what is broken
fozikio dashboard	live service and memory view
fozikio down	stop services it started

status and up use an HTTP probe rather than checking whether a process exists, because a wedged process still holds the port. They also adopt rather than kill: if fozikio did not start a process, it will not stop it — which matters when the Ollama desktop app or another agent already owns :11434.