Skip to content
FrameworkHunt

Research · analysis · added 4 Apr 2026

ARIS: Auto-Claude Code Research in Sleep — Deep Analysis

A research note, not a framework evaluation. It carries no architecture score and is not part of the directory or the comparison table.

ARIS is a methodology-first, Markdown-driven skill system for autonomous ML research workflows. It orchestrates cross-model collaboration — Claude Code executes research while an external LLM (Codex, Gemini, or other) reviews work as an adversarial critic. The entire system is files + plain Markdown skills (no database, no framework), making it portable across Claude Code, Cursor, Trae, Codex CLI, and other agents.

Noted

  • Claude Code executor reviews its own work → falls into local minima
  • Self-play is "stochastic bandits" (predictable failure modes)
  • Model converges to its own patterns, blind to alternative approaches

Source

← All research