shipwright-brain vs Global Agent Memory
shipwright-brain is a plugin bundle for AI coding tools published by shipwright-ai. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Global Agent Memory is an MCP server published by ozankasikci. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-18. 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
| Marketplace |  shipwright-brain |  Global Agent Memory |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 0.1.0 Forks (GitHub): 0 Stars (GitHub): 0 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.1.6 Downloads/month (PyPI): 132 Downloads/week (PyPI): 28 Forks (GitHub): 3 Stars (GitHub): 14 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
| Fact | shipwright-brain | Global Agent Memory |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 0 (worse) | 14 (better) |
| Forks (GitHub) (differs) | 0 (worse) | 3 (better) |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (global-memory-mcp) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | 2, secrets among them: 0 | Not published |
| Hooks it runs (differs) | 1 | Not published |
| Parts of the bundle (differs) | 3 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/shipwright-ai/shipwright-brain | github.com/ozankasikci/global-agent-memory |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-12 | 2026-10-11 |
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
shipwright-brain
Persistent memory for Claude Code. Markdown files, no database. Brain remembers ideas, decisions, features, and progress across sessions so Claude doesn't start from zero every time.
Global Agent Memory
Shared, project-aware memory for Claude Code, Codex, and other agents with human review.
How to run each
shipwright-brain As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install shipwright-brain@claude-communityGlobal Agent Memory As a local MCP server: PyPI package
claude mcp add --transport stdio global-agent-memory -- uvx global-memory-mcpCommands 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 Global Agent Memory publish no settings it asks for, so we do not compare settings.
What it can do: shipwright-brain · What it can do: Global Agent Memory · 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.