ARIS Automates Overnight ML Research Workflow

// 67d 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

67d ago

2026-03-21

PUBLISHED

67d ago

2026-03-21

RELEVANCE

8/ 10

AUTHOR

Github Awesome

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE2h ago

Cursor adds dedicated subagents for skills

Cursor now allows developers to execute tool-heavy or research-intensive agent skills within dedicated subagents. This architectural shift isolates noisy background tasks, keeping the main chat context clean and focused.

UPDATE2h ago

YouTube moves AI labels to video player

YouTube is moving its AI content disclosures from video descriptions to more prominent placements beneath the player and on Shorts overlays. Starting in May, the platform will use internal signals to automatically label photorealistic AI content that creators fail to disclose.

OPEN SOURCE5h ago

Taste Skill kills AI "frontend slop"

Taste-Skill is an open-source framework that provides portable "agent skills" to enforce high-end design principles in AI-generated code. By injecting specific design directives and "anti-slop" rules, it enables LLMs to produce editorial-grade UIs that bypass generic, boilerplate-heavy AI templates.