Scientific Research plugins, skills & connectors for Codex
5 scientific research listings on CodexStacks: 5 plugins (1 from the official OpenAI curated catalog; 4 community). Each page shows what the listing contains and how to install it, taken from its own source. 4 community listings had no declared category, so we assigned this one from the repo's topics and description.
Order: official OpenAI curated listings first (A–Z), then community repos by GitHub stars at last sync. This is not a quality ranking.
Boltz
Use Boltz from Codex for biomolecular modeling workflows: predict structure and binding for protein, RNA, DNA, and ligand complexes; rank small-molecule or protein libraries against targets; and design novel small molecules, peptides, antibodies, nanobodies, or custom protein binders with structures and confidence metrics.
simulink-agentic-toolkit
The Simulink Agentic Toolkit gives your AI agent both the tools and the expertise to work effectively with Simulink and Model-Based Design.
matlab-agentic-toolkit
The MATLAB Agentic Toolkit brings proven MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.
AutoSciRub
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
KERNEL
KERNEL is a Claude Code and Codex runtime for direct, decomposed execution with local memory and minimal hooks. Version 9.11.0 deploys the simplify deletion doctrine, preflight and verifier contract. Skills invoke as /kernel:<name> on Claude Code and $kernel:<name> on Codex; run /kernel:help first. Agent-readable summary: llms.txt.