Auto-claude-code-research-in-sleep

Auto-claude-code-research-in-sleep (ARIS) is a skill-based research workflow that can be used in Claude Code, Codex CLI, Cursor, Trae, Antigravity, GitHub Copilot CLI, OpenClaw, and DeepSeek Harness. The project describes itself as a methodology rather than a platform, emphasizing the research workflow. It states: "ARIS is a methodology, not a platform. What matters is the research workflow — take it wherever you go." and "Use ARIS as a skill-based workflow in Claude Code / Codex CLI / Cursor / Trae / Antigravity / GitHub Copilot CLI / OpenClaw / DeepSeek Harness — enjoy any way you like!"

In operation, an executor drives the workflow while an independent model, by default Codex MCP, reviews it. Alternative model combinations, including ModelScope-hosted models, do not require Claude or OpenAI API. The README says: "The executor drives, an independent model (Codex MCP by default) reviews. Alternative model combinations, including ModelScope-hosted models, need no Claude or OpenAI API."

ARIS can be installed as skills directly or as a standalone CLI and plugins. The repository notes that codex-cli 0.154.0 removed codex mcp-server, but ARIS now uses its own bridge over codex exec, preserving tools, results, 82 skills, and ultra and per-thread resume. It states: "Those are the skills installed directly. Want it in one command? ARIS also ships as a standalone CLI and as plugins:" and "the codex MCP server is now ARIS's own bridge over codex exec (mcp-servers/codex-exec/), same tools, same results, all 82 skills unchanged".