Marqo
Marqo is an AI-native ecommerce search and discovery platform, with an open-source multi-modal search engine repository maintained alongside it.
- GitHub stars
- 5k
- Last commit
- 1 mo ago
- Latest release
- 2.26.0
- Licence
- Apache-2.0
- Self-hosted
- Yes
- Hosted version
- Available

Marqo builds AI-native search and product discovery for online brands in categories such as fashion, beauty, electronics and home goods. Using semantic search and personalization, it learns from browsing clicks, orders and other events to infer what shoppers want and return relevant search results and recommendations.
The vendor says its platform helps commerce teams improve search relevance, raise conversion and order value, and reduce manual merchandising through automated ranking and optimization. The repository also hosts the open-source search engine project, with topics covering multi-modal search and machine learning. A notice at the top of the README clarifies the status of the open-source project relative to the commercial platform, so read it before adopting the code.
The code is written in Python under the Apache-2.0 license. You can run the open-source engine yourself, or buy the managed ecommerce platform from the vendor. It suits online retailers and developers evaluating vector search for product catalogs.
Key features
- Semantic product search
- Personalized search results and recommendations
- Clickstream and purchase data learning
- Automated ranking and merchandising
- Multi-modal search support
- Open-source engine in Python
