
Auto-claude-code-research-in-sleep
Skill-based research workflow where one model drives and another reviews, overnight
- Pricing
- Open source
- Platforms
- CLI, self-hosted
- GitHub stars
- 19.3K
- Last commit
- 3 days ago
- Language
- Python
- License
- MIT
About Auto-claude-code-research-in-sleep
Auto-claude-code-research-in-sleep is an open-source agent for research. It is available on CLI and self-hosted.
ARIS describes itself as a methodology rather than a platform. It is a set of skills, 82 at the time of the README, that let a coding agent run a research workflow while you sleep, with an independent model, Codex over MCP by default, acting as reviewer.
The skills install into Claude Code, Codex CLI, Cursor, Trae, Antigravity, GitHub Copilot CLI, OpenClaw and others, and it also ships as a standalone CLI and plugins. Alternative model pairings, including ModelScope-hosted models, avoid needing Claude or OpenAI APIs. A companion called SuperARIS adds a persistent team where a main agent coordinates engineering and writing in parallel.
The README notes a Codex CLI change that removed codex mcp-server, and says ARIS now ships its own bridge over codex exec, so reviewers need one re-registration.
What it does
- 82 research skills
- Skills cover the research workflow from ideas to writing.
- Executor and reviewer
- One model drives while an independent model reviews.
- Many host agents
- Works in Claude Code, Codex CLI, Cursor, Trae and more.
- Alternative models
- ModelScope-hosted models need no Claude or OpenAI API.
- Standalone CLI and plugins
- Install as skills, CLI or plugin.
- SuperARIS team mode
- A coordinating agent runs engineering and writing in parallel.
Good for
- Run an overnight literature and experiment loop
- Get an independent model to review an agent's research work
- Reuse the workflow in several coding agents
- Run research without Claude or OpenAI keys
Pricing
Open source
MIT licence
Auto-claude-code-research-in-sleep FAQ
Is it a platform?
No, the README calls it a methodology.
Which agents can run it?
Claude Code, Codex CLI, Cursor, Trae, Antigravity, GitHub Copilot CLI, OpenClaw and others.
Who reviews the work?
An independent model, Codex over MCP by default.
What licence is it?
MIT.
Is Auto-claude-code-research-in-sleep free?
Yes. Auto-claude-code-research-in-sleep is open source, so you can use and self-host it for free.
What are the best alternatives to Auto-claude-code-research-in-sleep?
The closest alternatives to Auto-claude-code-research-in-sleep are gemini-cli, deer-flow, ruflo, DeepCode and learn-claude-code.
Alternatives to Auto-claude-code-research-in-sleep

gemini-cli
AgentOpen-source terminal agent for Gemini Code Assist workflows on Google Cloud
- Open source
- Open-source agent
- 109K GitHub stars
- AI models and LLM tooling

deer-flow
AgentOpen-source super agent harness that researches, codes and creates with sandboxes
- Open source
- Open-source agent
- 85.4K GitHub stars
- AI models and LLM tooling

ruflo
AgentAgent meta-harness that adds swarms, memory and MCP tools to Claude Code and Codex
- Open source
- Agent framework
- 81.9K GitHub stars
- Knowledge and memory

DeepCode
AgentAutonomous framework that turns research papers into working code repositories
- Open source
- Open-source agent
- 16.8K GitHub stars
- Coding

learn-claude-code
AgentHands-on course teaching how to build the harness around an AI coding agent
- Open source
- Hosted agent
- 80.5K GitHub stars
- AI models and LLM tooling

openinterpreter
AgentTerminal coding agent tuned for low-cost and open-weight models
- Open source
- Open-source agent
- 68.9K GitHub stars
- Coding