Superduper
Superduper (formerly SuperDuperDB) is an open-source Python framework for building database-integrated AI agents and applications directly on top of existing databases - MongoDB, SQL databases, Snowflake, and Redis - without separate vector stores or ETL. It supports semantic / vector search, RAG, transformer and PyTorch model integration, LLM serving, and distributed ML workflows. The commercial side, Superduper Agents, is an enterprise AI agent orchestration platform for BI and data operations, distributed via the Snowflake Marketplace and self-hosted enterprise installs.
Superduper publishes 6 APIs on the APIs.io network. Tagged areas include AI Framework, Vector Search, RAG, LLMs, and MLOps.
Superduper’s developer surface includes documentation, GitHub presence, and 2 more developer resources.
APIs
Superduper Framework
Open-source Python framework (superduper-framework) for declaring AI models, embeddings, vector indexes, RAG pipelines, and listeners directly on top of an existing database. Ap...
Superduper MongoDB Plugin
Database backend plugin (superduper-mongodb) that turns a MongoDB cluster into a Superduper-managed AI datastore with vector search and model listeners.
Superduper SQL Plugin
Database backend plugin (superduper-sql) for SQL databases - PostgreSQL, MySQL, SQLite, DuckDB, and other SQLAlchemy-supported engines.
Superduper Snowflake Plugin
Database backend plugin (superduper-snowflake) that runs Superduper against a Snowflake account, including the Snowflake Marketplace distribution path for Superduper Agents.
Superduper Redis Plugin
Database backend plugin (superduper-redis) for Redis-backed Superduper deployments.
Superduper Agents
Commercial enterprise AI agent orchestration product for BI and data operations. Connects to 40+ databases, data warehouses, and business tools - PostgreSQL, MongoDB, Snowflake,...