Hugging Face vs autoresearch
Hugging Face is an MCP server published by docker. Marketplaces we read that list it: 1 (Docker MCP Catalog). autoresearch is a plugin bundle for AI coding tools published by pjhoberman. Marketplaces we read that list it: 2 (Claude Code: claude-plugins-community, Community GitHub marketplaces). As of our marketplace pass on 2026-10-20. 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 |  Hugging Face |  autoresearch |
|---|---|---|
| Docker MCP Catalog | Listed Version: not stated No figure published Not marked · First seen |
Not listed |
| Claude Code: claude-plugins-community | Not listed | Listed Version: 1.2.0 Forks (GitHub): 1 Stars (GitHub): 22 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 | Hugging Face | autoresearch |
|---|---|---|
| Marketplaces that list it (differs) | 1 (worse) | 2 (better) |
| Stars (GitHub) (differs) | No figure on GitHub | 22 |
| Forks (GitHub) (differs) | No figure on GitHub | 1 |
| Last release | Not published | Not published |
| Where it runs (differs) | Remote server (huggingface.co/mcp) | Installs as a plugin bundle |
| Transport (differs) | Streamable HTTP | Not stated |
| Tools it declares (differs) | 4 | Not published |
| Environment variables it asks for | Not published | Not published |
| Parts of the bundle (differs) | Not a bundle | 2 |
| Licence (differs) | Apache-2.0 | MIT |
| Repository (differs) | Not stated | github.com/pjhoberman/autoresearch |
| Changes in the last 7 days (differs) | 0 | 2 |
| First seen | 2026-10-11 | 2026-10-11 |
| Endpoint at the last check (differs) | Responded 4 days ago | no remote endpoint we check |
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
Hugging Face
Tools for interacting with Hugging Face models, datasets, research papers, and more.
autoresearch
Autonomous experiment loops on any codebase — one file, one metric, one loop. An agent edits a constrained file, runs an eval, keeps improvements, reverts failures, and repeats unattended. Based on Karpathy’s autoresearch pattern, generalized beyond ML training to any code with a measurable outcome.
How to run each
Hugging Face As a remote MCP server
claude mcp add --transport http hugging-face https://huggingface.co/mcpautoresearch As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install autoresearch@claude-communityCommands built only from what the marketplaces declare; the full set for every client is on each card.
Only Hugging Face has a remote endpoint we check. How we check endpoints
Tools each declares
Neither the marketplaces of autoresearch nor its endpoint list any 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: Hugging Face · What it can do: autoresearch · Compare two other plugins
Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. 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.