Auto-claude-code-research-in-sleep

View on GitHub

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.

★ 17K1,403 forksPythonMITwanshuiyin

ARIS is a Markdown-only skill pack for autonomous ML research that plugs into Claude Code, Codex, Cursor, OpenClaw or any LLM agent. It adds cross-model review loops, idea discovery, experiment automation and paper writing skills, plus a Codex MCP bridge, with no framework lock-in.

Use Cases

Run autonomous ML research overnight via agent skillsCross-model review loops where one LLM reviews another's workAutomated research idea discovery and novelty checkingML experiment automation and GPU setup orchestrationAutomated academic paper writing and figure generationPeer-review-style paper critique and scoringResubmit-and-rebuttal workflow for conference submissionsSession recovery and watchdog for long-running agent runsMonitor agent sessions on macOS for approval promptsModel-agnostic agent workflow across Claude Code, Codex, Cursor, Trae

Built With

Language: Python
Frameworks: Claude Code · Codex CLI · Cursor · Trae · Antigravity · GitHub Copilot CLI · OpenClaw · DeepSeek Harness · MCP · OpenRouter · ModelScope · MiniMax MCP

Auto-claude-code-research-in-sleep

Use Cases

Built With

Tags