# wanshuiyin/Auto-claude-code-research-in-sleep

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

Repository: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
Canonical: https://ross.abutalabs.com/products/auto-claude-code-research-in-sleep
Language: Python
License: MIT
License Family: permissive
Topics: ai-research, autonomous-agent, claude-code, codex, mcp, ml-research, paper-review, research-automation, ai-tools, claude, gpt, llm, machine-learning, openai, paper-writing, claude-code-skills, deep-learning, idea-generation, mcp-server, aris
Last push: 2026-08-26T09:30:40+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 98, longevity 12
- inputs: {"age_days": 176, "days_push": 7, "days_rel": 12, "gap_med": 0.0, "n_releases_24m": 41}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15293, forks 1340 (observed 2026-08-28T04:11:09.520279+00:00)

## What it is
ARIS is a collection of lightweight Markdown-only skills that turn LLM coding agents (Claude Code, Codex, Cursor, etc.) into autonomous ML research assistants. It provides cross-model review loops, research idea discovery, and experiment automation without any framework lock-in.

## Use cases
- run autonomous ML research experiments overnight with an LLM agent
- set up cross-model paper review loops between Claude and Codex
- generate and triage research ideas with an AI agent
- automate ML experiment workflows inside Claude Code
- write and review research papers using agent skills
- use the same research methodology across different LLM coding tools

## When to choose
- you already use Claude Code, Codex CLI, Cursor, or similar LLM agents and want research automation
- you want a framework-free, Markdown-only workflow you can adapt to any agent
- you need structured review loops and experiment automation for ML research

## When to avoid
- you need a turnkey GUI or hosted research platform rather than agent skills
- your work is not ML/AI research oriented
- you are not comfortable driving experiments through a terminal-based LLM agent

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, prompt-engineering, workflow-automation, developer-tools
- domain: artificial-intelligence, machine-learning, developer-tools
- platform: cli, cross-platform, python
- tags: claude-code-skills, autonomous-research, llm-agent-workflow, paper-review, idea-generation, experiment-automation, markdown-skills, model-agnostic, ai-agents, research-automation

## Member repositories
- wanshuiyin/Auto-claude-code-research-in-sleep (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:09.520279+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:06:23.156777+00:00, confidence not recorded.
  - readme: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep (fetched 2026-08-28T04:11:09.520279+00:00, sha f9ec368f0b65)
- Data as of 2026-08-30T08:39:29.467469+00:00.