ARIS is an open-source AI workflow that automates scientific research, from literature review and idea generation to experimental deployment and self-review.
ARIS (Auto-claude-code-research-in-sleep) is an open-source, automated scientific research workflow inspired by FARS. It aims to streamline the research process by integrating AI agents for various tasks. The system is designed to be lightweight, primarily utilizing Claude Code and Codex CLI, and has been adapted to work with GLM5 and Minimax2.5. The workflow consists of two main parts: the first focuses on literature summarization, idea generation, and initial experimental deployment, incorporating 'idea-creator' and 'novelty check' skills. The second part involves an 'auto-review-loop' where Claude Code, using MCP to call Codex GPT 5.4 Xhigh as a reviewer, iteratively refines the research by reviewing, debugging, running experiments, and re-reviewing for up to four rounds until predefined standards are met or the maximum rounds are reached. The developers emphasize that while ARIS accelerates research, it does not replace human critical thinking and domain expertise.
Integrations: Claude Code, Codex CLI, GLM5, Minimax2.5, GPT 5.4 Xhigh
Platforms: Web
View full ARIS (Auto-claude-code-research-in-sleep) profile on Tools-Radar | Browse Research tools | Alternatives to ARIS (Auto-claude-code-research-in-sleep)
Tools-Radar is a free directory of 10,000+ AI tools — discover, compare, and choose the right AI software for your needs. Visit tools-radar.com