Ext Ops Panel
Open dashboard
Comparison

agent-memory vs Cortex Memory Engine

agent-memory is a plugin bundle for AI coding tools published by Keshab0310. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Cortex Memory Engine is an MCP server published by gambletan. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-13. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplaceagent-memoryCortex Memory Engine
Claude Code: claude-plugins-community Listed
Version: 0.1.0
Forks (GitHub): 2
Stars (GitHub): 3
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 1.8.0
Forks (GitHub): 3
Stars (GitHub): 35
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

agent-memory vs Cortex Memory Engine
Factagent-memoryCortex Memory Engine
Marketplaces that list it11
Stars (GitHub) (differs)3 (worse)35 (better)
Forks (GitHub) (differs)2 (worse)3 (better)
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleOn your machine (ghcr.io/gambletan/cortex:v1.8.0)
Transport (differs)Not statedstdio
Tools it declaresNot publishedNot published
Environment variables it asks for (differs)2, secrets among them: 0Not published
Hooks it runs (differs)2Not published
Parts of the bundle (differs)4Not a bundle
Licence (differs)MITNot stated
Repository (differs)github.com/keshab0310/agent-memorygithub.com/gambletan/cortex
Changes in the last 7 days00
First seen2026-10-112026-10-11

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

agent-memory

In its own words, on Claude Code: claude-plugins-community:

Save 60-90% on LLM token costs with intelligent memory compression. agent-memory automatically compresses tool output into structured observations, shares context across agents via a memory bus, and injects only relevant memory into each prompt — keeping your token budget under control. Features: auto-compression hooks (PostToolUse), token-budgeted context injection (SessionStart), semantic search via FTS5, cross-session persistence, and a token economics dashboard showing compression ratios and savings.

Cortex Memory Engine

In its own words, on Official MCP Registry:

Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs.

How to run each

agent-memory As a Claude Code plugin

Claude Code
/plugin marketplace add anthropics/claude-plugins-community
/plugin install agent-memory@claude-community

Cortex Memory Engine As a local MCP server: Docker image

Claude Code
claude mcp add --transport stdio cortex -- docker run -i --rm ghcr.io/gambletan/cortex:v1.8.0

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

The marketplaces of Cortex Memory Engine publish no settings it asks for, so we do not compare settings.

What it can do: agent-memory · What it can do: Cortex Memory Engine · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built