claude

autoscience

Autoresearch loop: skill, tools and live dashboard

2 on GitHubby Miles McGuirev0.4.0MITupdated 1 month ago
/

Plugin autoscience from marketplace claude-autoresearch in minuteman3/claude-autoresearch. Commands read from the repo's manifest — 28 days ago.

What it installs

Skills (1)

  • autoresearch

    Autonomous optimize-measure-keep/discard loop against a single numeric metric (test runtime, bundle size, latency, loss, binary size, print time…). Use when the user says "autoresearch", "optimize X overnight", "keep trying ideas until Y improves", "run experiments on", or wants an unattended improv

View source on GitHub

Similar plugins

Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/autoresearch-agent:setup, /ar-run, /ar-loop, /ar-status, /ar-resume), 8 built-in evaluators, configurable loop intervals (10min to monthly).

6 skills · 1 agent · hooks

alirezarezvani/claude-skills 29,725

Autonomous research orchestration using a two-loop architecture. Manages the full research lifecycle from literature survey to paper writing, routing to domain-specific skills for execution. Use when starting a research project, running autonomous experiments, or managing multi-hypothesis research.

98 skills

Orchestra-Research/AI-Research-SKILLs 14,502

autoresearch

claudecodex

Autonomous improvement engine. 14 commands with bounded defaults, chain handoff, and adaptive evals checkpoints. 95% token reduction via modular architecture.

1 skill · 14 commands · hooks

uditgoenka/autoresearch 6,833

Autonomous skill optimizer using Karpathy's autoresearch methodology. Scores outputs 0-100, mutates prompts, keeps improvements. Includes auto-screenshot and stop-gate hooks.

ccplugins/awesome-claude-code-plugins 1,005

Autonomous research loop inspired by karpathy/autoresearch — give it a plain-language goal; it infers a recommended contract, then grills each decision with you (goal measurability, artifact, evaluator, bounds) before iterating: cheap sequential rounds that escalate to a parallel GAN tournament when they plateau

3 commands · hooks

FradSer/dotclaude 596

Autonomous experiment workflow with a shared Claude Code/Codex skill, validated state, bounded continuation, and measured keep/discard rules

1 skill · 1 command · hooks

drivelineresearch/autoresearch-claude-code 351

Maintain autoscience?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted