AgentStack

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

by ARIS:

8
researchVisit

Description

**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.

Weaknesses

  • -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

Tags

researchtypescriptpythonopen-sourcepapermcpllm
License: (Check GitHub for license)Added: 2026-04-04

Related Tools