Orchestra-Research/AI-Research-SKILLs Alternatives

choose it if you want a large multilingual academic research skills library with an MIT license.

A curated, multilingual library of 182 installable AI agent skills for end-to-end academic research—spanning literature discovery, scientific writing, grant development, bioinformatics, drug discovery, clinical research, machine learning, and data analysis.

choose it if you want a lightweight, markdown-only, framework-free skills library.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

choose it if you want skills that encode a research supervisor's guidance from idea to submission.

将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。

choose it if you want a lean end-to-end academic research workflow for Claude Code.

Academic Research Skills for Claude Code: research → write → review → revise → finalize

choose it if you want a turn-key autonomous research pipeline instead of assembling skills into an agent.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

choose it if you want a self-evolving system that autonomously drives a research project from idea to paper.

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

choose it if you want the improved v2 with agentic tree search for deeper exploration.

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

choose it if you want an interactive human-in-the-loop research workflow.

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

choose it if you want a blueprint-driven runtime for reproducible, orchestrated research workflows.

A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.

choose it if you want a native Apple Silicon (MLX) implementation without PyTorch.

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

choose it if you want self-organizing agent teams for long-running experiments.

AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation

choose it if you want a Claude Code-driven implementation of the Kosmos AI scientist.

Kosmos: An AI Scientist for Autonomous Discovery - An implementation and adaptation to be driven by Claude Code or API - Based on the Kosmos AI Paper - https://arxiv.org/abs/2511.02824

choose it if you want a standalone autonomous AI research assistant.

🦞+🔬 NanoResearch: The Autonomous AI Research Assistant

choose it if you use the pi agent and need a specialized autonomous experiment loop.

Autonomous experiment loop extension for pi

choose it if you need 24/7 experiment monitoring and execution rather than a full research suite.

🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.

choose it if your work is in bioinformatics and life sciences and you need domain-specific skills.

197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.

choose it if you focus only on automated paper writing and evaluation.

An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.