Upgini
For machine learning pipelines, Upgini searches and enriches data with features from public and commercial sources.
About Upgini
Upgini is an open-source Python library for data search and enrichment for machine learning pipelines. It searches public, community-shared, and premium external sources, including open and commercial language models, and generates features using LLMs, graph neural networks, and recurrent neural networks.
It is used with tabular data for binary classification, multiclass classification, regression, and time-series prediction, with a scikit-learn-compatible interface. Enrichment is based on search keys such as date, country, postal/ZIP code, phone number, hashed email, and IP address, and listed coverage totals 239 countries and up to 41 years of history, varying by source.
Key features
- Searches public, community-shared, and premium external data sources
- Generates features with LLMs, RNNs, and graph neural networks
- Enriches datasets using date, country, postal code, IP, phone, hashed email
- Augments missing search keys from connected sources
- Calculates accuracy metrics and uplift after enrichment
- Checks accuracy gain stability on out-of-time verification data
Best for: Data scientists working with tabular supervised models who need external features for training data.
Good for
- Open-source library with scikit-learn-compatible interface for existing pipelines
- Connects to public, community-shared, and premium sources in one request
- Includes checks for accuracy uplift and stability on verification intervals
Watch out for
- Enrichment requires supported search keys such as date, country, or postal code
- Use is limited to listed tabular tasks: binary, multiclass, regression, time-series
Upgini at a glance
- Website
- github.com/upgini/upgini
- Category
- Development › Developer Tools
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Guides for Developer Tools
Upgini alternatives
Tools and sites you could use instead, ranked by how closely they match.
Machine learning pipelines can use whylogs, an open-source library for logging data quality and model performance.
Open source
24 alternatives
mlxtend adds helper modules for Python data analysis and machine learning libraries.
SynapseML provides distributed machine learning algorithms for Spark through its Python library.
Open source
24 alternatives
Class-imbalanced machine learning is supported by imbalanced-ensemble, a toolbox for ensemble methods and datasets.
Open source
24 alternatives
Python developers can use Streamlit to build and share data applications.
FreeOpen source
24 alternatives
The Geni project provides a Clojure dataframe library that runs on Apache Spark.
Open source
24 alternativesPopular in Developer Tools
Well-known listings from the same topic.
AppDevToolsappdevtools.comCommand Not Foundcommand-not-found.comTestFlighttestflight.apple.com/join/A8GwCnq8Sourcegraphabout.sourcegraph.comProject Wallaceprojectwallace.comCarbon Calculatorwebsitecarbon.com
Upgini FAQ
What search keys can Upgini use for enrichment?
Date/datetime, phone number, postal/ZIP code, hashed email, country, and IP address.
Which machine learning tasks are supported?
Binary classification, multiclass classification, regression, and time-series prediction on tabular data.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.