autonomous ML research / agent skill workflows
ARIS is a lightweight Markdown-only skill collection for autonomous ML research—idea discovery, experiment automation, and cross-model paper review—designed to plug into LLM coding agents like Claude Code and Codex.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Broader AI research & engineering skill library with the same Markdown approach; pick it when you need extra engineering coverage beyond ARIS.
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Standalone Leader-Worker agent that runs experiments 24/7; choose it for a self-running system rather than agent-integrated skills.
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
Blueprint-driven AutoResearch runtime for programmatic orchestration of full research workflows, instead of composable skills.
A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
Fully autonomous self-evolving idea-to-paper system with its own runtime; choose it for a turnkey pipeline.
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
Autonomous experiment loop built specifically for the pi agent; use it if pi is your host.
Autonomous experiment loop extension for pi
MLX-optimized port of the original autoresearch loop for Apple Silicon; choose it for a PyTorch-free Mac-native loop.
Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.
End-to-end autonomous research workflow as a Python framework with human assistance; use it for a standalone pipeline.
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Focused deep-research skill with human-in-the-loop for information gathering, not ML experiment automation.
Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control
Skill set for the academic paper write-review-revise-finalize pipeline, no experiment automation.
Academic Research Skills for Claude Code: research → write → review → revise → finalize
Minimal Claude Code skill for modify-verify-keep iteration without ARIS's idea discovery and paper review tools.
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
Codex-specific lightweight autoresearch skill, narrower than ARIS (no cross-model review/idea discovery).
Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
In-editor multi-agent tool for academic writing/review/editing, if you want a GUI plugin rather than a headless skill.
A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
These projects were analysed and named Auto-claude-code-research-in-sleep among their alternatives. The relationship is not symmetric — how Auto-claude-code-research-in-sleep rates them is a separate judgement, made when Auto-claude-code-research-in-sleep is analysed in its own right.
calls Auto-claude-code-research-in-sleep “choose it if you want a lightweight, markdown-only, framework-free skills library.”
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
calls Auto-claude-code-research-in-sleep “Markdown-only, no-framework peer; pick it when you want cross-model review loops and unattended overnight ML runs instead of Light-skills' human-confirmation gates.”
An AI workflow skill pack for research, competitions, and innovation projects.
calls Auto-claude-code-research-in-sleep “choose for fully autonomous ML research loops instead of human-in-the-loop skills”
Academic Research Skills for Claude Code: research → write → review → revise → finalize
calls Auto-claude-code-research-in-sleep “When you want lightweight, Markdown-only research skills for ML experiments without a heavy framework.”
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.
calls Auto-claude-code-research-in-sleep “narrower: Claude Code skills for ML research, not a pi-general loop.”
Autonomous experiment loop extension for pi
calls Auto-claude-code-research-in-sleep “autonomous ML research skill pack; choose it for hands-off idea/experiment loops rather than interactive engineering habits”
🥷 Engineering habits you already know, turned into skills Claude can run.
calls Auto-claude-code-research-in-sleep “Markdown-only Claude Code skills implementing a research loop; pick it for ML research automation only, with no general devops agent support.”
The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.
calls Auto-claude-code-research-in-sleep “markdown skill pack that needs Claude Code to run, not a standalone system.”
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞