OPEN_SOURCE ↗
YT · YOUTUBE// 21d agoOPENSOURCE RELEASE
ARIS Automates Overnight ML Research Workflow
Auto Claude Code Research in Sleep, also called ARIS, is an open-source set of Markdown-only Claude Code skills for autonomous ML research. The project frames the workflow as a sleep-friendly research loop: the agent can score a paper, surface weaknesses, run experiments, and rewrite the narrative before you wake up, while staying lightweight and portable across Claude Code, Codex CLI, OpenClaw, and other LLM agents.
// ANALYSIS
Hot take: this is less a single app than a sharp, opinionated research operating system, and the cross-model review loop is the most compelling part because it adds a real critic instead of letting one model self-affirm.
- –Plain Markdown skills keep the system portable and easy to fork.
- –Cross-model review via Codex MCP is a strong guardrail against self-review blind spots.
- –The workflow covers the full research arc: idea discovery, experiment execution, review, and paper writing.
- –The main risk is that autonomy can amplify bad assumptions if human checkpoints are too loose.
// TAGS
claude-codeautonomous-researchresearch-automationmcpmarkdown-skillsllmagent
DISCOVERED
21d ago
2026-03-21
PUBLISHED
21d ago
2026-03-21
RELEVANCE
8/ 10
AUTHOR
Github Awesome