Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 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.
Repository Index
47,133 repositories indexed
1–24 of 24 · Most stars
Data Apps & Dashboards for Python. No JavaScript Required.
Official git repository for Biopython (originally converted from CVS)
A full spaCy pipeline and models for scientific/biomedical documents.
🦖 ClawBio - The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Open. Free.
Cloud-native genomic dataframes and batch computing
ADAM is a genomics analysis platform with specialized file formats built using Apache Avro, Apache Spark, and Apache Parquet. Apache 2 licensed.
Plant phenotyping with image analysis
Python package for graph neural networks in chemistry and biology
In-memory nucleotide sequence k-mer counting, filtering, graph traversal and more
Interactive network visualization in Python and Dash, powered by Cytoscape.js
Lightweight, super fast C/C++ (& Python) library for sequence alignment using edit (Levenshtein) distance.
Graph-linked unified embedding for single-cell multi-omics data integration
A dependency-free cross-platform swiss army knife for PDB files.
Native R and Python sample-deletion robustness for omics: candidate certificates, minimum deletion bounds, Bioconductor model refits and donor-level pseudobulk
A tool for cell instance aware segmentation in densely packed 3D volumetric images
CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework
TypeDB Bio: Biomedical Knowledge Graph
NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions
Autonomous multi-agent framework to optimize scientific software
MCP server for spatial transcriptomics analysis through natural language interfaces.
Fast, deterministic cell-type deconvolution for million-bin spatial transcriptomics
UV-first benchmark for protein-ligand docking with reproducible annotation, pocket similarity, and HPC workflows.
Bioinformatics-themed kata for practicing string manipulation in a data transformation pipeline. Contains replit files to work quickly in an online dojo setting.