automated scientific discovery / AI scientist
The AI Scientist is a system that uses LLMs to autonomously conduct scientific research, from idea generation to paper writing.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Direct successor with agentic tree search; choose for the improved workshop-level version.
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Same goal via self-organizing agent teams; choose if you want long-running multi-agent experimentation.
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Alternative implementation based on the Kosmos paper; choose if you prefer that architecture or Claude Code integration.
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
Different approach focused on backward-traceable data-to-paper; choose if traceability is a priority.
data-to-paper: Backward-traceable AI-driven scientific research
These projects were analysed and named AI-Scientist among their alternatives. The relationship is not symmetric — how AI-Scientist rates them is a separate judgement, made when AI-Scientist is analysed in its own right.
calls AI-Scientist “choose for end-to-end fully automated paper generation rather than a Claude Code skill suite”
Academic Research Skills for Claude Code: research → write → review → revise → finalize
calls AI-Scientist “A standalone automated discovery framework; use if you want a simpler all-in-one AI scientist, not a skill set.”
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
calls AI-Scientist “choose it if you want a turn-key autonomous research pipeline instead of assembling skills into an agent.”
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 AI-Scientist “A runnable Python framework that executes the whole idea-to-paper loop unattended; choose it over composable skill files if you can live with 9-month-old code and a non-standard license.”
An AI workflow skill pack for research, competitions, and innovation projects.
calls AI-Scientist “choose v1 when you have a clear template and want higher paper-success rates for well-defined tasks.”
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search