Memory (Reference) vs self-improving-agent
Memory (Reference) is an MCP server published by modelcontextprotocol. Marketplaces we read that list it: 1 (Docker MCP Catalog). self-improving-agent is a plugin bundle for AI coding tools published by Alireza Rezvani. Marketplaces we read that list it: 1 (Community GitHub marketplaces). As of our marketplace pass on 2026-10-16. 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 |  Memory (Reference) | |
|---|---|---|
| Docker MCP Catalog | Listed Version: sha256:db0c2db07a44 Forks (GitHub): 11 788 Pulls (Docker Hub): 557 120 Stars (Docker Hub): 26 Stars (GitHub): 91 289 Not marked · First seen |
Not listed |
| Community marketplace alirezarezvani/claude-skills | Not listed | Listed Version: 2.9.1 Forks (GitHub): 3 996 Stars (GitHub): 28 271 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 | Memory (Reference) | self-improving-agent |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 91 289 (better) | 28 271 (worse) |
| Pulls (Docker Hub) (differs) | 557 120 | No figure on Docker Hub |
| Forks (GitHub) (differs) | 11 788 (better) | 3 996 (worse) |
| Last release | Not published | Not published |
| Where it runs (differs) | On your machine (mcp/memory) | Installs as a plugin bundle |
| Transport (differs) | stdio | Not stated |
| Tools it declares (differs) | 9 | Not published |
| Environment variables it asks for | Not published | Not published |
| Hooks it runs (differs) | Not published | 1 |
| Parts of the bundle (differs) | Not a bundle | 9 |
| Licence (differs) | NOASSERTION | MIT |
| Repository (differs) | github.com/modelcontextprotocol/servers | github.com/alirezarezvani/claude-skills |
| Changes in the last 7 days (differs) | 0 | 2 |
| First seen (differs) | 2026-10-11 | 2026-10-14 |
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
Memory (Reference)
Knowledge graph-based persistent memory system.
self-improving-agent
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract patterns into skills. Ships 5 slash commands (/si:memory-review, /si:promote, /si:extract, /si:memory-status, /si:remember) and 2 sub-agents (memory-analyst, skill-extractor).
How to run each
Memory (Reference) As a local MCP server: Docker image
claude mcp add --transport stdio memory -- docker run -i --rm mcp/memoryself-improving-agent As a Claude Code plugin
/plugin marketplace add alirezarezvani/claude-skills
/plugin install self-improving-agent@claude-code-skillsCommands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
The marketplaces of self-improving-agent publish no list of tools, so we do not compare tools.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: Memory (Reference) · What it can do: self-improving-agent · Compare two other plugins
Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.