OpenData is a collection of open source databases built on a common, object-native storage and infrastructure foundation.

Benchmark and optimize LLM inference across frameworks with ease

The API to search, scrape, and interact with the web at scale. 🔥

Real-time analytics on Postgres tables

Serialization format for row-based incremental data processing

Kafka Streams Topology Design (KSTD) is an open standard dedicated to the clear and effective description and visualization of Kafka Stream topologies.

cdebug - a swiss army knife of container debugging

A data modelling layer built on top of polars and pydantic

TTS with kokoro and onnx runtime

A blazing fast inference solution for text embeddings models

Generic command line non-JVM Apache Kafka producer and consumer

Fluent API for assertions supporting pytest, designed with simplicity and ease of use in mind.

Open-source Dropbox client for macOS and Linux

LLMPerf is a library for validating and benchmarking LLMs

A high-throughput and memory-efficient inference and serving engine for LLMs

Comparison of Language Model Inference Engines

A collection of YAML files, Helm Charts, Operator code, and guides to act as an example reference implementation for NVIDIA NIM deployment.

Deploy Kafka pipelines to Kubernetes

A Go framework for services and agents

The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.

A demo to accompany our blogpost "Scalable Machine Learning with Kafka Streams and KServe"

🏗 Build container images for your Java applications.

The Fastest Way to Create Live Data Products

Use JSON-Schema with React, generate Forms + UIs with any design system, easy creation of complex custom widgets.

Static checker for GitHub Actions workflow files

Run your GitHub Actions locally 🚀

A delightful and complete interface to GitHub's amazing API

Open-source offline translation library written in Python

Python Stream Processing. A Faust fork