RAGStack
github.com
- Free plan
- Windows
- macOS
- Linux
- Self-hosted
What RAGStack is
RAGStack is a curated set of open-source software for building retrieval-augmented generation applications. Its Python packages install with `pip install ragstack-ai`, and the stack uses the LangChain ecosystem. Astra DB Serverless and Apache Cassandra are supported as vector stores. The documentation names RAG fusion and FLARE as available advanced techniques, and gives an example using RAGStack with Astra DB and OpenAI. LangSmith compatibility supports monitoring AI deployments. DataStax selects component versions and checks compatibility, performance and security across them; it also scans components for known vulnerabilities. The documentation describes caching AI calls and Astra DB parallelism as ways to help with performance, scalability and cost. RAGStack is free and open source at no cost. Enterprise support and SLAs, as well as support for HIPAA, TRUSTe and SOC 2, apply when it runs in Astra DB. One limitation for TypeScript projects is that its package contains only a subset of LangChain libraries, so some projects may need to retain additional `@langchain/*` packages.
Who it suits
RAGStack suits developers building RAG applications with LangChain and Astra DB Serverless or Apache Cassandra. Teams using TypeScript should check whether the included LangChain subset covers their needs.
Good to know, and what to watch
- Free and open source.
- Supports Astra DB Serverless or Apache Cassandra.
- Includes RAG fusion and FLARE techniques.
- Compatible with LangSmith monitoring.
- Components are checked together and scanned for vulnerabilities.
- TypeScript package includes only a subset of LangChain libraries.
- Enterprise support and listed compliance support apply in Astra DB.
Plans
Every plan and priceRAGStack
Open source
The verdict
RAGStack provides a ready-selected set of components and techniques for building RAG applications. Its TypeScript package has a stated scope limit, and enterprise support and listed compliance support depend on running it in Astra DB.
What the maker publishes
- Compatibility checks
- DataStax selects component versions and tests their compatibility, performance, and security together. source
- Compliance
- The documentation says enterprise support and SLAs, and support for HIPAA, TRUSTe, and SOC 2, apply when running RAGStack in Astra DB. source
- Founded
- 2010 source
- Framework
- RAGStack leverages the LangChain ecosystem and is compatible with LangSmith for monitoring AI deployments. source
- Headquarters
- Santa Clara, California, United States source
- Install
- The Python packages can be installed with `pip install ragstack-ai`. source
- Migration limit
- The TypeScript package includes only a subset of LangChain libraries, so projects may need to retain other `@langchain/*` packages. source
- Performance
- The documentation says caching AI calls and Astra DB parallelism can help with performance, scalability, and cost. source
- Purpose
- RAGStack is a curated stack of open-source software for building production-ready retrieval-augmented generation applications. source
- RAG techniques
- The documentation names RAG fusion and FLARE as advanced techniques available with RAGStack. source
- Security scans
- DataStax says it scans all RAGStack components with industry-standard tools for known vulnerabilities. source
- Support
- The documentation describes enterprise support and SLAs for RAGStack when running in Astra DB. source
- Usage example
- DataStax documents a RAG example using RAGStack, Astra DB, and OpenAI. source
- Vector stores
- RAGStack supports Astra DB Serverless or Apache Cassandra as a vector store. source
Checked against the maker's pages on 8 Oct 2026.