agent-loops vs auto-research
agent-loops is a plugin bundle for AI coding tools published by gaasher. Marketplaces we read that list it: 1 (Community GitHub marketplaces). auto-research is a plugin bundle for AI coding tools published by gyoz-ai. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). As of our marketplace pass on 2026-10-23. 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 |  auto-research | |
|---|---|---|
| Community marketplace gaasher/agent-loop-skills | Listed Version: 0.1.0 Forks (GitHub): 19 Stars (GitHub): 177 Not marked · First seen |
Not listed |
| Claude Code: claude-plugins-community | Not listed | Listed Version: 1.0.0 Forks (GitHub): 0 Stars (GitHub): 3 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 | agent-loops | auto-research |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 177 (better) | 3 (worse) |
| Forks (GitHub) (differs) | 19 (better) | 0 (worse) |
| Last release | Not published | Not published |
| Where it runs | Installs as a plugin bundle | Installs as a plugin bundle |
| Transport | Not stated | Not stated |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Parts of the bundle (differs) | 25 | 1 |
| Licence | MIT | MIT |
| Repository (differs) | github.com/gaasher/agent-loop-skills | github.com/gyoz-ai/auto-research |
| Changes in the last 7 days (differs) | 2 | 0 |
| First seen (differs) | 2026-10-19 | 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
agent-loops
Drop-in agentic loop skills (autoresearch, literature & writing, data, optimization, red-team, power analysis). Skills install namespaced as agent-loops:<name>.
auto-research
Autonomous skill improvement through parallel research agents. Inspired by Karpathy's autoresearch methodology, it spawns 5 parallel agents (domain expert, quality auditor, competitive analyst, gap analyst, tech scout), synthesizes findings into ranked proposals, then runs an iterative keep/discard experiment loop to improve any Claude Code skill. Scores skills on 7 quality dimensions and only keeps changes that genuinely improve the composite score.
How to run each
agent-loops As a Claude Code plugin
/plugin marketplace add gaasher/agent-loop-skills
/plugin install agent-loops@agent-loop-skillsauto-research As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install auto-research@claude-communityCommands 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
Neither one's marketplaces publish the settings it asks for.
What it can do: agent-loops · What it can do: auto-research · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.