AI & ML

Extends pandas for geospatial vector data analysis, including reading/writing shapefiles, GeoJSON, GeoPackage, and PostGIS, performing spatial joins, geometric operations, coordinate transformations, and creating static or interactive maps.

Automates hypothesis generation and testing on tabular datasets using LLMs, combining data-driven discovery with literature integration for scientific research.

Parse PDFs, Office files, and images locally with layout-preserved text, bounding boxes, OCR, and page screenshots for RAG and multimodal agents.

Train quantum circuits like neural networks with automatic differentiation, device-independent programming, and integration with PyTorch or JAX.

Train reinforcement learning agents at millions of steps per second using optimized PPO, vectorized environments, and multi-agent support.

Build and train graph neural networks for drug discovery, protein modeling, and molecular science using PyTorch-native tools.

Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Fetch feeds, read papers, leave feedback, and export data using the pz CLI.

Perform high-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames, including overlap, nearest, merge, coverage, complement, subtract, and reading/writing BED, VCF, BAM, GFF, FASTA, and FASTQ formats with streaming and cloud-native support.

Provides deep generative models for single-cell omics analysis, including probabilistic batch correction, transfer learning, differential expression, and multi-modal integration.

Perform nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows using the umap-learn library.

Fit statistical models (OLS, GLM, ARIMA, mixed models) with detailed diagnostics, residuals, and inference for econometrics and time series analysis.

Store and process large N-dimensional arrays with chunking, compression, and parallel I/O, integrating with NumPy, Dask, and Xarray for cloud-native scientific computing.

Build and evaluate machine learning models using scikit-learn for classification, regression, clustering, dimensionality reduction, and preprocessing.

Load pre-trained models from Hugging Face Hub, run pipeline inference, generate text, and fine-tune models on NLP, vision, audio, and multimodal tasks using the Transformers library.

Analyze any text to extract a cognitive fingerprint across 12 dimensions, revealing reasoning patterns, decision styles, and thinking signatures.

Generate and edit high-quality images using OpenRouter's AI models including FLUX.2 Pro and Gemini 3.1 Flash Image Preview.

Discovers and uses scientific datasets, models, blog posts, and interactive demos from a curated catalog for AI/ML work in domains like biology, chemistry, physics, and genomics.

Perform survival analysis and time-to-event modeling in Python using scikit-survival, including Cox models, random survival forests, gradient boosting, survival SVMs, and evaluation metrics like concordance index and Brier score.

Build and train graph neural networks with PyTorch Geometric, covering node/link/graph classification, message passing layers, heterogeneous graphs, and custom datasets.

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data, enabling efficient access to cell metadata, gene expression slices, summary counts, and embeddings without downloading whole datasets.

Analyze and engineer protein glycosylation by scanning sequences for N-glycosylation sequons, predicting O-glycosylation hotspots, and accessing curated glycoengineering tools for therapeutic antibody optimization and vaccine design.

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, and other RAPIDS libraries for dramatic speedups on numerical, data, ML, graph, and simulation workloads.

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server, returning 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions.

Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard, MLflow), and distributed training (DDP, FSDP, DeepSpeed) for scalable neural network training.

Train reinforcement learning agents using PPO, SAC, DQN, TD3, DDPG, and A2C algorithms with a scikit-learn-like API. Supports custom Gymnasium environments, vectorized environments, callbacks, and model persistence.

Forecast any univariate time series (sales, sensors, energy, vitals, weather) zero-shot using Google's TimesFM foundation model, with point forecasts and prediction intervals from CSV, DataFrame, or array inputs.

Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface, covering loading, preprocessing, drift correction, spike sorting, quality metrics, and unit curation.

Guides statistical hypothesis testing with assumption checks, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting for research data.

Formulate testable hypotheses from observations, design experiments, and generate predictions using a structured scientific method framework.

Create publication-quality scientific diagrams using AI generation with smart iterative refinement and quality review.

Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase.

Handles git and GitHub operations using the gh CLI, triggered by any github.com URL. Covers creating and reviewing PRs, watching CI checks, interactive rebasing, branch cleanup, submodule management, and repository archaeology.

Improves AI skills for activation, clarity, and cross-model reliability through benchmarking, salience tuning, and regression triage.

Designs complex generic types, refactors `any` types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors.

Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.

Model threat actors, intrusion sets, campaigns, and TTPs as a STIX 2.1 knowledge graph in OpenCTI using the pycti Python client, connectors, and import workers for structured cyber threat intelligence.