# Autoresearch AI Plugin

> Autonomous experiment loop for Claude Code. Run an endless optimize-measure-keep/discard cycle on any optimization target: LLM training loss, test speed, bundle size, build time, and more.

## Facts
- Page: https://tashan.sh/capability/plugin-proyecto26-autoresearch-ai-plugin-autoresearch-ai-plugin
- tashan id: plugin:proyecto26/autoresearch-ai-plugin/autoresearch-ai-plugin
- Source: https://github.com/proyecto26/autoresearch-ai-plugin
- Type: plugin
- Category: devtools
- tashan score: 40.0 / 100
- Adoption: 21.0
- Upkeep: 56.0
- Freshness: 81.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: solid
- GitHub stars: 12
- License: MIT
- Official: no

## Install

```sh
/plugin marketplace add anthropics/claude-plugins-community
/plugin install autoresearch-ai-plugin@claude-community
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-13 by tashan (https://tashan.sh) from public evidence. Scorer s5.