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.
ARIS (Auto-Research-In-Sleep) is a Markdown-only, framework-free methodology for automating machine learning research workflows, distributed as a set of skill files that run inside Claude Code, Codex CLI, Cursor, and other LLM agent runtimes without requiring any proprietary platform. Its core loop assigns three roles to the agent: a breadth pass for idea discovery and literature scanning, a cross-model adversarial review step where multiple models critique drafts, and a research wiki that persists findings as structured memory across sessions. Concrete slash-commands include `/render-html` for generating fact-checked HTML write-ups, `/paper-talk` for producing presentation slides, and `/homepage-generator` for building academic homepages from CV data. The project also ships ARIS-Monitor, a dependency-free Python floating window that flags which Claude Code sessions are waiting for user authorization. Researchers and ML practitioners who want unattended overnight experiment tracking, automated paper drafting, and cross-model peer review without adopting a heavyweight framework are the primary audience.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleepAwesome Lists overview
# Auto-claude-code-research-in-sleep (ARIS ⚔️🌙)
<p align="center">
<a href="https://huggingface.co/papers/2605.03042">
<img src="docs/hf_daily_paper_1.svg" alt="Hugging Face Daily Paper · #1 Paper of the Day" width="360">
</a>
</p>
[](https://huggingface.co/papers/2605.03042) · [](https://wanshuiyin.github.io/Auto-claude-code-research-in-sleep/ARIS_INTRO.html) · [](docs/aris_intro_slides.pdf) · [](AGENT_GUIDE.md) · [](https://mp.weixin.qq.com/s/tDniVryVGjDkkkWl-5sTkQ) · [](https://github.com/VoltAgent/awesome-agent-skills) · [-orange?style=flat)](https://aidigitalcrew.com) · [](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/stargazers) · [💬 Join Community](#community) · [](#citation)
💡 *Use ARIS as a skill-based workflow in [Claude Code](https://docs.anthropic.com/en/docs/claude-code) / [Codex CLI](skills/skills-codex/) / [Cursor](docs/CURSOR_ADAPTATION.md) / [Trae](docs/TRAE_ARIS_RUNBOOK_EN.md) / [Antigravity](docs/ANTIGRAVITY_ADAPTATION.md) / [GitHub Copilot CLI](docs/COPILOT_CLI_ADAPTATION.md) / [OpenClaw](docs/OPENCLAW_ADAPTATION.md), or get the full experience with the standalone CLI — enjoy any way you like!*
🌱 *ARIS is a methodology, not a platform. What matters is the research workflow — take it wherever you go.*
🔥 *ARIS natively fits any agent's **ultracode-style deep mode** — the breadth/firepower pass adapts to the runtime (Claude Code ultracode + workflows on Opus 4.8, Codex `spawn_agent`, or plain sequential), feeding three roles: **breadth · cross-model review → accuracy · research wiki → memory**.*
*However a loop is driven, it reports to the same cross-model jury + research wiki — **it can drive, never acquit**.*
🤖 **AI agents:** Read [`AGENT_GUIDE.md`](AGENT_GUIDE.md) instead — structured for LLM consumption, not human browsing.
🚀 **Beyond 科研 → 任何 "研究"**：[**ARIS-Anything**](https://github.com/wanshuiyin/ARIS-Anything) 把 ARIS 的五步 loop（plan / draft / 对抗审 / 迭代 / 持久化）推广到非学术的结构化研究——投资尽调 / 法律研究 / 市场研究 / 自驱学习 / 调查新闻 / 工程复盘等。
🎯 **准备 2026 AI 秋招？** → [**🌐 ARIS-in-AI-Offer**](https://wanshuiyin.github.io/ARIS-in-AI-Offer/) · [GitHub repo](https://github.com/wanshuiyin/ARIS-in-AI-Offer) · [中文 README](https://github.com/wanshuiyin/ARIS-in-AI-Offer/blob/main/README_CN.md) —— 23 篇双语 ML / LLM / 多模态 / 生成式 / Agent 面试 cheat sheet，每篇 = 公式推导 + 从零 PyTorch + 25 高频面试题（L1 / L2 / L3），全部由 ARIS 的 `/render-html` 自动生成。**希望大家秋招轻松一点 🌱**
<p align="center">
<a href="https://github.com/wanshuiyin/ARIS-in-AI-Offer">
<img src="https://raw.githubusercontent.com/wanshuiyin/ARIS-in-AI-Offer/main/assets/preview_strip.jpg" alt="ARIS-in-AI-Offer preview — ① Foundations + ② Interview Q&A + ③ From-Scratch Code, three columns from a representative cheat sheet" width="100%">
</a>
</p>
> 📖 *Preview from the [Diffusion Foundations cheat sheet](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/diffusion_foundations_tutorial.html) — every tutorial in [ARIS-in-AI-Offer](https://github.com/wanshuiyin/ARIS-in-AI-Offer) follows the same three-pillar structure (foundations / interview Q&A / runnable code).*
>
> 🌐 *Same workflow, different deliverable — [**ARIS-Homepage v1 live demo**](https://wanshuiyin.github.io/) (CV → fact-checked single-file academic homepage via `/homepage-generator`).*
>
> 📝 *Three long-form blogs, cross-model collaborative writing via `/render-html` — [Continuous DLM — a representation-perspective survey (2026 H1)](https://wanshuiyin.github.io/ARIS-in-AI-Offer/blogs/continuous_dlm_representation_perspective.html) · [Cosmos 3 — understanding + generation in one Transformer (MoT)](https://wanshuiyin.github.io/ARIS-in-AI-Offer/blogs/cosmos3_mot_guide.html) · [Diffusion × representation × manifold learning](https://wanshuiyin.github.io/ARIS-in-AI-Offer/blogs/diffusion_representation_manifold.html).*
🛰 **社区好物 · [Claude Fleet](https://github.com/tianyilt/claude-fleet)**（by [@tianyilt](https://github.com/tianyilt)）—— 一个本地**只读**数据看板，同时盯住你开的一堆 **Claude Code / Codex** 窗口：triage（谁在干活 / 等你点权限 / 跑完了）· 一键 **Focus** 跳到对应终端 · ~50ms 全文搜所有 transcript · skill / memory 用量分析。像 ARIS 这种动辄并行一片 agent 的工作流特别合适。**好用的话点个 ⭐**
🪟 **更轻的自家选择 · [ARIS-Monitor](aris-monitor/)** —— 不想开浏览器？ARIS 自带一个 macOS 置顶**悬浮小窗**(纯 Python stdlib,**无浏览器 · 无 Chrome 扩展**):只盯"**哪个会话在等你授权**" 🔴,点一行直接跳到那个终端。**Claude Fleet = 全功能网页看板;ARIS-Monitor = 同一想法的极简常驻版**,各取所需。
<table align="center" width="100%">
<tr>
<td width="66%" align="center" valign="top">
<a href="https://github.com/tianyilt/claude-fleet"><img src="assets/claude-fleet-preview.png" width="100%" alt="Claude Fleet — full local web dashboard for many concurrent Claude Code / Codex windows (triage, Focus, full-text search, skill/memory analytics)"></a>
</td>
<td width="34%" align="center" valign="top">
<a href="aris-monitor/"><img src="aris-monitor/assets/screenshot.png" width="100%" alt="ARIS-Monitor — minimal always-on-top floating widget showing which Claude Code sessions need approval (calm all-clear vs red ATTENTION)"></a>
</td>
</tr>
<tr>
<td align="center"><b><a href="https://github.com/tianyilt/claude-fleet">Claude Fleet</a></b> · 全功能网页看板</td>
<td align="center"><b><a href="aris-monitor/">ARIS-Monitor</a></b> · 极简悬浮小窗(自带)</td>
</tr>
</table>
<details>
<summary><b>Run ARIS-Monitor in 5 seconds</b></summary>
```bash
# part of this repo — no extra clone, no pip install, no browser:
cd aris-monitor && ./run.sh
# a borderless panel floats top-right; click a row to jump to that terminal
```
</details>
<details>
<summary><b>Run Claude Fleet in 30 seconds</b></summary>
```bash
git clone https://github.com/tianyilt/claude-fleet
cd claude-fleet && bash run.sh
# open http://127.0.0.1:7878 in your browser
```
</details>
🔥 [**ARIS-Code CLI — 独立安装版**](docs/ARIS-Code-README_CN.md) · [English](docs/ARIS-Code-README_EN.md) | [⬇️ Download](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/releases/latest)
<table>
<tr>
<td valign="top" width="60%">
📰 **ARIS-Code v0.4.5 → v0.4.16** (2026-05/06) — a twelve-release polish run: **new providers** (DeepSeek V4 Pro / Xiaomi MiMo / Qwen 3.6 / Doubao / Custom OpenAI-compatible / DashScope), **first-class reasoning + tool-use**, **stream + MCP reliability** (closes [#228](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/228) / [#151](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/151) / [#172](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/172) / [#249](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/249)), **REPL history + Ctrl+R search** ([#274](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/274)), **security hardening** (system-prompt secret redaction; opt-in `sandbox.strictMode`, [#238](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/238); subagent credential-leak guard), **multi-provider pricing**, **skills bundle + drift-CI sync**, and assorted fixes ([#232](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/232) DeepSeek deprecation, PermissionMode silent-allow, hardcoded date, reviewer reset). Per-release detail below. Credits: [@GetIT-Sunday](https://github.com/GetIT-Sunday), [@Anduin9527](https://github.com/Anduin9527), [@GO-player-hhy](https://github.com/GO-player-hhy), [@Jxy-yxJ](https://github.com/Jxy-yxJ), [@screw-44](https://github.com/screw-44), [@StevenUST](https://github.com/StevenUST), [@opposj](https://github.com/opposj), [@ShijunLei-cn](https://github.com/ShijunLei-cn), [@algojogacor](https://github.com/algojogacor).
</td>
<td valign="top" width="40%">
<img src="docs/aris-code-banner.png" width="100%" alt="ARIS-Code CLI terminal — Auto Research in Sleep">
</td>
</tr>
</table>
> <details><summary>Per-release details (v0.4.5 → v0.4.16)</summary>
>
> **v0.4.16** (2026-05-30) — REPL UX + provider hardening, shipped under a zero-regression discipline: 64 characterization ("golden") tests locked the *current* provider-routing / pricing / reviewer / subagent / REPL behavior first, then stayed green through every change. Closes [#274](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/274): command history now persists to `~/.config/aris/history` (0600) and reloads on startup, with an `ARIS_NO_HISTORY` kill-switch and a disk-only secret-skip (credential-looking lines stay in in-session history but never touch disk); bash-style **Ctrl+R** reverse incremental search (CJK display-width-aware single-line render; no existing key binding changed; no new dependency). Security: an OpenAI-family main session (Kimi / GLM / MiniMax / …) spawning a subagent previously **silently billed the user's Anthropic OAuth/Keychain credential** — it now fails loud with a clear, credential-free error; full OpenAI-family subagent routing is a cross-crate change deferred to v0.4.17. Groundwork (noWhat people ask about Auto-claude-code-research-in-sleep
What is wanshuiyin/Auto-claude-code-research-in-sleep?
+
wanshuiyin/Auto-claude-code-research-in-sleep is awesome lists for the Claude AI ecosystem. 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. It has 12k GitHub stars and was last updated yesterday.
How do I install Auto-claude-code-research-in-sleep?
+
You can install Auto-claude-code-research-in-sleep by cloning the repository (https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is wanshuiyin/Auto-claude-code-research-in-sleep safe to use?
+
Our security agent has analyzed wanshuiyin/Auto-claude-code-research-in-sleep and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains wanshuiyin/Auto-claude-code-research-in-sleep?
+
wanshuiyin/Auto-claude-code-research-in-sleep is maintained by wanshuiyin. The last recorded GitHub activity is from yesterday, with 48 open issues.
Are there alternatives to Auto-claude-code-research-in-sleep?
+
Yes. On ClaudeWave you can browse similar awesome lists at /categories/awesome, sorted by popularity or recent activity.
Deploy Auto-claude-code-research-in-sleep to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/wanshuiyin-auto-claude-code-research-in-sleep)<a href="https://claudewave.com/repo/wanshuiyin-auto-claude-code-research-in-sleep"><img src="https://claudewave.com/api/badge/wanshuiyin-auto-claude-code-research-in-sleep" alt="Featured on ClaudeWave: wanshuiyin/Auto-claude-code-research-in-sleep" width="320" height="64" /></a>More Awesome Lists
A collection of MCP servers.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and plugins for Claude Code by Anthropic
Installable GitHub library of 1,500+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes specialized plugins, installer CLI, bundles, workflows, and official/community skill collections.