cassio
A framework-agnostic Python library to seamlessly integrate Apache Cassandra(R) with ML/LLM/genAI workloads.
Decision gist · record as of 2026-08-14
Yes, if you are already committed to Cassandra or Astra DB and need to integrate it with LLM/ML workloads. The permissive Apache license, low install friction, and active repository support the choice. However, be aware of the aging maintenance cadence (680 days since last release) and the possibility of breaking changes in the 0.* series. Not recommended if you need a stable, frequently-updated vector database abstraction—consider alternatives if stability and rapid feature iteration are priorities.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later.
- Requires a running Apache Cassandra cluster (5+) or Astra DB instance to connect to.
- Low install friction with pure-Python wheels.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions, making it suitable for most production and proprietary projects.
last release 2024-10-03 (680 days) · last repo commit 2025-11-24 · 109 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 353,185 downloads/mo, #7,305 on PyPI
Alternatives
Verify before relying
pip install cassio
import cassio
# Requires cassandra-driver, requests, numpy as runtime dependencies
# See cassio.org for integration examples with LangChain and other frameworks- Whether the alpha-stage designation in the description reflects current stability despite the Production/Stable classifier
- Performance characteristics and scalability limits for typical ML/LLM workloads
- Completeness of vector search and embedding storage capabilities relative to specialized vector databases
What it is and what it does
cassIO is a Python library that bridges Apache Cassandra and AI/LLM workloads, letting you store and query data for machine learning and generative AI applications using Cassandra as the backend. It's designed to be framework-agnostic, meaning it works alongside existing LLM frameworks like LangChain rather than replacing them. The library depends on cassandra-driver for database connectivity, requests for HTTP operations, and numpy for numerical operations.
The package is currently at version 0.1.10 and classified as Production/Stable despite being labeled an alpha release in its documentation. It supports Python 3.9 through 3.12 and requires a live Cassandra cluster (version 5+) or Astra DB instance. Development is active but infrequent—the last release was over 680 days ago, though the repository shows recent commits. Breaking changes are possible given the 0.* versioning.
Use it for
- Store embeddings and vectors in Cassandra for retrieval-augmented generation (RAG) pipelines with LLMs
- Build LangChain applications backed by Cassandra for persistent, scalable AI data storage
- Integrate machine learning feature stores with Cassandra for training and inference workflows
- Query and manage structured data alongside AI models in a single Cassandra cluster
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are already committed to Cassandra or Astra DB and need to integrate it with LLM/ML workloads.
The permissive Apache license, low install friction, and active repository support the choice. However, be aware of the aging maintenance cadence (680 days since last release) and the possibility of breaking changes in the 0.* series. Not recommended if you need a stable, frequently-updated vector database abstraction—consider alternatives if stability and rapid feature iteration are priorities.
Install
cassio on PyPI
Before you install
Low install friction with pure-Python wheels. Maintenance status is aging—680 days since last release, though the repository remains active with recent commits. Expect occasional breaking changes given the 0.* version.
Requires Python 3.9 or later. Requires a running Apache Cassandra cluster (5+) or Astra DB instance to connect to.
License in practice
Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions, making it suitable for most production and proprietary projects.
Quickstart
pip install cassio
import cassio
# Requires cassandra-driver, requests, numpy as runtime dependencies
# See cassio.org for integration examples with LangChain and other frameworksVerify before relying
- Whether the alpha-stage designation in the description reflects current stability despite the Production/Stable classifier
- Performance characteristics and scalability limits for typical ML/LLM workloads
- Completeness of vector search and embedding storage capabilities relative to specialized vector databases
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <4.0,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 3 packagescassandra-driverrequestsnumpy |
| Maintenance | Aging 680 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 353,185 / month, #7,305 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: cassio-0.1.10-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “cassandra llm integration”
- cassiocassIO integrates Apache Cassandra with machine learning and LLM…
- langchain-astradbIntegrates Astra DB (a serverless vector database built on Apache…
- apache-airflow-providers-apache-cassandraIntegrates Apache Cassandra with Apache Airflow, providing operators…
Give your agent the search over MCP, or paste the wish link into any chat.
More Scientific/Engineering packages
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
pandas provides fast, flexible data structures (Series and DataFrame) for loading, cleaning, transforming, and analyzing labeled or relational data in Python.
scipy provides numerical algorithms for mathematics, science, and engineering—including optimization, integration, linear algebra, Fourier transforms, signal and image processing, and ODE solvers—built on numpy arrays.
scikit-learn provides a comprehensive Python library for supervised and unsupervised machine learning, including classification, regression, clustering, dimensionality reduction, and model evaluation tools built on NumPy and SciPy.
Install it if you need to train, evaluate, or deploy supervised or unsupervised learning models.
dill extends Python's pickle module to serialize and deserialize a much wider range of Python objects, including functions, lambdas, classes, and interpreter sessions, to byte streams for storage or network transmission.
Multiprocess is an enhanced fork of Python's standard multiprocessing library that uses dill for better serialization, allowing you to spawn processes with a threading-like API and share complex objects between them.
Install it if you use multiprocessing and encounter pickle serialization limits with lambdas or complex objects.
See also cassandra-driver · scylla-driver · langchain-oci · acsylla · langchain-astradb · apache-airflow-providers-apache-cassandra · onnxruntime-genai · lunary · astra-assistants · mlflow