Software

Software we have developed to help non-domain experts access to our algorithms

Heelo Dev

Heelo is an infrastructure platform that gives AI agents a unified API for performing real-world actions—such as booking travel, ordering products, sending outreach messages, posting to social media, scheduling appointments, and processing payments—through a single tool call instead of complex browser automation or multi-step workflows. Rather than requiring agents to orchestrate dozens of browser interactions and LLM reasoning steps, Heelo abstracts these tasks into reliable, high-level actions, substantially reducing token usage, latency, cost, and maintenance overhead. The platform integrates with popular agent frameworks through both MCP and SDK interfaces, allowing developers to equip AI agents with production-ready capabilities across services such as Amazon, Shopify, Booking.com, Expedia, LinkedIn, X, Instagram, Gmail, and Stripe while providing a consistent authentication and execution model.

Topcited AI

TopCited is a generative engine optimization (GEO) platform that helps businesses measure and improve how often their products and brands are recommended by AI search systems such as ChatGPT, Gemini, Claude, and Perplexity. It combines AI visibility monitoring with content optimization, tracking metrics such as recommendation frequency, ranking, sentiment, competitor comparisons, and citation sources. Beyond analytics, TopCited uses its research-based CORE optimization framework to rewrite and generate website content, simulate how AI models rank and cite information, and iteratively improve content before publication to maximize the likelihood of being recommended by AI assistants. The platform also provides website audits, content generation, competitive reports, and educational resources, positioning itself as an end-to-end solution for improving AI search visibility rather than simply monitoring it.

MyDataPilot

MyDataPilot is an AI-powered data science assistant that enables anyone to perform sophisticated data analysis without coding or machine learning expertise. Simply describe what you want to analyze in plain English, and MyDataPilot handles everything from data loading to generating publication-ready visualizations. Work directly with your local files - no uploading required - while maintaining complete transparency over the AI's decision-making process. Watch each step of the AI's reasoning, modify its approach as needed, and download professional Python scripts for future use. Whether you're analyzing sales trends, discovering customer insights, or cleaning messy datasets, MyDataPilot transforms complex data science tasks into simple conversations, making expert-level analysis accessible to everyone.

GenePrep

GenePrep is an automated multi-agent system that revolutionizes the preprocessing and analysis of large-scale gene expression data from GEO and TCGA databases. By simply installing the package, users can execute end-to-end workflows including data validation, trait-condition pair selection, statistical testing, and comprehensive result generation - all with minimal manual scripting. Given a dataset and trait-condition pairs, GenePrep intelligently identifies genes associated with specific traits while properly accounting for experimental conditions. Its modular agent architecture enables iterative planning, execution, and debugging, dramatically reducing preprocessing overhead while improving reproducibility. Built on research presented in "Toward a Team of AI-made Scientists for Scientific Discovery from Gene Expression Data" and the GenoTEX benchmark, GenePrep represents a significant leap forward in automating genomic data analysis and accelerating scientific discovery.

Robustar

Robustar is an interactive toolbox designed to support precise data annotation and robust vision learning through an intuitive visual interface. Unlike traditional black-box machine learning systems, Robustar empowers users to understand and improve their models through a transparent, iterative workflow. Import your trained models and test samples, then leverage influence functions to identify which training samples most impact predictions. Use integrated saliency maps to visualize exactly which image regions drive model decisions, then employ drawing tools to mask out superficial or misleading pixels. These refined annotations serve as augmented training data for continued model improvement. This human-in-the-loop approach enables researchers and practitioners to build more robust vision models by systematically identifying and correcting the features their models rely on, bridging the gap between model performance and genuine understanding of visual concepts.