Task Observer — One Skill to Rule Them All vs io.github.cdeust/hypermnesia-mcp
Task Observer — One Skill to Rule Them All is a plugin bundle for AI coding tools published by Eoghan Henn. Marketplaces we read that list it: 1 (Community GitHub marketplaces). io.github.cdeust/hypermnesia-mcp is an MCP server published by cdeust. Marketplaces we read that list it: 3 (Official MCP Registry, PyPI (MCP servers), Community GitHub marketplaces). As of our marketplace pass on 2026-11-10. 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 |  io.github.cdeust/hypermnesia-mcp | |
|---|---|---|
| Community marketplace rebelytics/one-skill-to-rule-them-all | Listed Version: 3.10.0 Forks (GitHub): 383 Stars (GitHub): 3 818 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 4.23.5 Downloads/month (PyPI): 1 993 Downloads/week (PyPI): 135 Forks (GitHub): 16 Stars (GitHub): 76 Not marked · First seen |
| PyPI (MCP servers) | Not listed | Listed Version: 4.23.5 Downloads/month (PyPI): 1 993 Downloads/week (PyPI): 135 Forks (GitHub): 16 Stars (GitHub): 76 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 | Task Observer — One Skill to Rule Them All | io.github.cdeust/hypermnesia-mcp |
|---|---|---|
| Marketplaces that list it (differs) | 1 (worse) | 3 (better) |
| Stars (GitHub) (differs) | 3 818 (better) | 76 (worse) |
| Forks (GitHub) (differs) | 383 (better) | 16 (worse) |
| Last release (differs) | 2026-11-06 | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (hypermnesia-mcp) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 3, secrets among them: 0 |
| Hooks it runs (differs) | Not published | 12 |
| Parts of the bundle (differs) | Not published | 26 |
| Licence (differs) | CC-BY-4.0 | MIT |
| Repository (differs) | github.com/rebelytics/one-skill-to-rule-them-all | github.com/cdeust/cortex |
| Changes in the last 7 days (differs) | 2 | 0 |
| First seen (differs) | 2026-11-03 | 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
Task Observer — One Skill to Rule Them All
Turns the corrections and repeated workflows of your work sessions into small, reviewed skill updates: every change comes with its evidence and a written reason, and nothing touches a skill until you approve and install it.
io.github.cdeust/hypermnesia-mcp
Persistent memory for AI agents — 36 cited neuroscience mechanisms, local-first, hybrid retrieval.
How to run each
Task Observer — One Skill to Rule Them All As a Claude Code plugin
/plugin marketplace add rebelytics/one-skill-to-rule-them-all
/plugin install task-observer@one-skill-to-rule-them-allio.github.cdeust/hypermnesia-mcp As a local MCP server: PyPI package
claude mcp add --transport stdio hypermnesia-mcp -- uvx hypermnesia-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 Task Observer — One Skill to Rule Them All publish no settings it asks for, so we do not compare settings.
What it can do: Task Observer — One Skill to Rule Them All · What it can do: io.github.cdeust/hypermnesia-mcp · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Package data comes from the Python Package Index (pypi.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.