---
title: "copilot-autoresearch"
description: "Run measurable, resumable experiment loops with Copilot CLI tools, commands, and skills."
canonical: https://agentpluginsdirectory.com/plugins/copilot-autoresearch
last-updated: 2026-10-05
---

# copilot-autoresearch
Run measurable, resumable experiment loops with Copilot CLI tools, commands, and skills.
- Slug: copilot-autoresearch
- Publisher: Mike Wallio
- Repository: https://github.com/scaryrawr/scarypilot
- Manifest: plugins/copilot-autoresearch/plugin.json
- Version: 0.2.6
- Category (editorial): other
- Skills: 2 (autoresearch-create, autoresearch-finalize)
- MCP servers: 0
- Stars: 5
- Repository created: 2026-02-12
- Repository last pushed: 2026-10-03
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/copilot-autoresearch
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What copilot-autoresearch does, in the publisher's words

A Copilot CLI extension that recreates the pi-autoresearch workflow: an autonomous experiment loop where the agent tries an idea, benchmarks it, keeps what works, reverts what doesn't, and repeats, without stopping until you tell it to.

> Try an idea, measure it, keep what works, discard what doesn't, repeat forever.

- A current GitHub Copilot CLI release with plugin extension support.
- Git, Node.js, and Bash available in the repository where experiments run.

Autoresearch executes benchmark commands and intentionally creates Git commits or reverts experiment changes in the active repository. Use it only in a repository whose changes you are prepared to let the agent modify.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/scaryrawr/scarypilot/HEAD/plugins/copilot-autoresearch/README.md