ARIS

v1.0.0Coding Agentsstable

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.

ai-researchai-toolsarisautonomous-agentclaude
Share:
10,322
Stars
0
Downloads
0
Weekly
0/5

What is ARIS?

ARIS is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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 wi...

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.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only

Use Cases

Autonomous ML research
Experiment automation
Cross-model review loops
wanshuiyin

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx auto-claude-code-research-in-sleep

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use ARIS

ARIS (Auto-Research-In-Sleep) is a collection of over 79 composable Markdown-only skills for autonomous machine learning research that works with Claude Code, Codex, OpenClaw, and other LLM agents. It orchestrates complete research pipelines — from literature search and novelty verification through experiment execution on local or remote GPUs to paper writing, peer-review response generation, and conference talk preparation. Because it uses no framework or library lock-in, the skills drop directly into any agent's skills directory and chain together through inline configuration parameters.

Prerequisites

  • Claude Code, Codex, or another LLM agent that supports a skills directory
  • Git to clone the repository
  • An EXA_API_KEY for web search capabilities (optional but recommended)
  • A GEMINI_API_KEY for AI-generated paper illustrations (optional)
  • ARIS_VERIFY_EMAIL set for CrossRef academic API polite pool access (optional)
1

Clone the ARIS repository

Clone the repository to get the full skill set and installer tools.

git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git
2

Install skills into your project (recommended)

Run the install script pointing to your project directory. This creates a local symlink so updates are easy to pull in.

bash Auto-claude-code-research-in-sleep/tools/install_aris.sh ~/your-project
3

Install skills globally (alternative)

Copy the skills directly into Claude Code's global skills directory to make them available across all projects.

cp -r Auto-claude-code-research-in-sleep/skills/* ~/.claude/skills/
4

Set optional environment variables

Export the API keys that unlock additional capabilities. Add these to your shell profile or CLAUDE.md for persistence.

export EXA_API_KEY=your-exa-api-key
export GEMINI_API_KEY=your-gemini-api-key
export [email protected]
5

Configure a remote GPU (optional)

For experiment execution on a remote server, add GPU configuration to your project's CLAUDE.md file. ARIS supports local GPUs, SSH remote servers, and on-demand Vast.ai provisioning.

# Add to CLAUDE.md:
gpu: remote
gpu_host: [email protected]
gpu_port: 22
gpu_workspace: /path/to/workspace
conda_hook: source ~/miniconda3/bin/activate research
6

Run your first research pipeline

Open Claude Code and invoke the /research-pipeline skill with a research topic. Append inline overrides to control effort level, reviewer model, and other parameters.

ARIS Examples

Client configuration

ARIS installs as agent skills, not a traditional MCP server. This shows how to configure Codex as a cross-model reviewer via MCP alongside ARIS.

{
  "mcpServers": {
    "codex": {
      "command": "codex",
      "args": ["mcp-server"]
    }
  }
}

Prompts to try

Invoke ARIS skills in Claude Code using these prompts. Append parameters with double-dash syntax.

- "/research-pipeline 'factorized gap in discrete diffusion LMs'"
- "/research-pipeline 'improve method X' -- ref paper: https://arxiv.org/abs/2406.04329"
- "/rebuttal 'paper/ + reviews' -- venue: ICML, character limit: 5000"
- "/paper-talk 'paper/' -- venue: ICLR, assurance: conference-ready"
- "/exa-search 'latest advances in diffusion models 2024'"

Troubleshooting ARIS

Skills not found after installation

Verify the skills were copied to the correct directory for your agent (e.g., ~/.claude/skills/ for Claude Code). Run 'ls ~/.claude/skills/' and confirm the ARIS skill files are present. Reload your agent after installing.

Research pipeline stalls waiting for reviewer

The default reviewer is Codex (GPT-5.5). If Codex is unavailable, switch to manual review mode: append '-- reviewer: manual' to your pipeline command. This pauses for you to paste the review into any model.

EXA search or paper fetch fails with API errors

Confirm EXA_API_KEY is exported in your shell (echo $EXA_API_KEY). If ARIS_STREAM_IDLE_TIMEOUT_SECS is too short for slow connections, increase it: export ARIS_STREAM_IDLE_TIMEOUT_SECS=300

Frequently Asked Questions about ARIS

What is ARIS?

ARIS is a Model Context Protocol (MCP) server that 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 connects AI assistants to external tools and data sources through a standardized interface.

How do I install ARIS?

Follow the installation instructions on the ARIS GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with ARIS?

ARIS works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is ARIS free to use?

Yes, ARIS is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "auto-claude-code-research-in-sleep": { "command": "npx", "args": ["-y", "auto-claude-code-research-in-sleep"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use ARIS?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides