Data Science and AI implementations that make business sense
Supertype Incubator
Product Factory
Supertype Incubator is the in-house product factory of Supertype, a team of highly creative data scientists and AI engineers who just love to build and hack on things. It is the birthplace for several of Supertype products, and is a place where Supertype members actualize their ideas into AI applications with absolute freedom and autonomy.
Incubated Products
Sectors Financial Data Suite
•Supertype Fellowship
•Supertype Collective
•Supertype Summary
Sectors Financial Data Suite
Financial AI, Agentic Workflows and Financial Data APIs
Sectors is a financial data infrastructure that enable financial institutions to automate their data workflows, market research, and AI model development. It offers pluggable APIs for AI developers, enabling them to build financial chatbots and agentic AI models in mere minutes. Since inception it has been used by 500+ financial workflows, and the Sectors Financial API service has seen more than 1 million invocations.
Supertype Fellowship
Open-source, community-driven peer-to-peer learning
Peer-to-peer learning, but with 🥇 badges, timelines, points and elective-based curations. The Supertype Fellowship platform is developed to be an open-source backbone of the Fellowship program, where participants learn by writing code, creating features, and shipping code to complete one of 10+ electives under mentorship and peer support.
Supertype Collective
Community of analytics developers and AI engineers
Also an open source platform, Supertype Collective is a community of analytics developers, AI engineers and engineering leaders building products across the full stack. It features a block-based Components and Hooks system to create stunning developer profiles that look great on every devices and exportable to PDF.
Supertype Summary
App Store insights delivered as PowerPoints in 60 seconds
A report generation engine that generates beautiful 30-page PDF reports from any Google Play or App Store URL in under 100 seconds. In addition to sentiment scoring, it uses a keyword extractor routine developed in-house to group reviews into topic groups (“unfriendly paywall”, “long tutorial”, “app crashes”, “poor customer service”, “very fast loading time” etc), and assign importance scores to each group.
Open Source
Supertype Organization on GitHub
We have several open-source projects that we maintain on GitHub. These are projects that we have built for our own use and have decided to share with the community. Unless specified otherwise, all projects are released under the MIT license. Clone, fork and contribute back with a Pull Request if you find them useful.
Large Language Models (LLM) Python Series
A set of 40+ instructional materials, code samples, Python scripts and guides featuring project-based LLMs through interfaces like LangChain, LlamaIndex, Chroma and Pinecone. 250,000 learners and counting.
Source CodeRead Documentation on GithubSuperinference
Superinference is a library that infers analysis-ready attributes from a person's social media username or unique identifier and returns them as JSON objects.
Source Codepip install superinferencenpm install superinferenceelang Language Embeddings
Elang is an acronym that combines the phrases Embedding (E) and Language (Lang) Models. Its goal is to help NLP (natural language processing) researchers, Word2Vec practitioners, LLM educators and data scientists be more productive in training language models and explaining key concepts in word embeddings.
Source Codepip install elangEmail Network
Utilities for inspecting, visualizing and exploring exported mailboxes (Gmail and Outlook's default .mbox) along with graphing utilities built on top of NetworkX.
Source Codepip install emailnetworkWordpress-posts-React
A lightweight (no-dependencies, <3 kb minified!) set of React hooks and components to asynchronously fetch and display WordPress posts using WordPress's most updated REST API
Source Codenpm install wordpress-posts-reactYouTube Analytics Python wrapper
A set of Python scripts for producing analytics using the YouTube Analytics API
Source CodeRead Documentation on Github
