Stars
🌡️ AI-Powered Air Quality Index (AQI) prediction system for Karachi, Pakistan, featuring automated data collection, ML model training, and real-time forecasting with Fronted and Backend.
Kolada MCP: Connect your LLM via remote server URL or local installation to access official statistics for Swedish municipalities and regions.
Distribute and run AI workloads on Kubernetes magically in Python, like PyTorch for ML infra.
The observability platform for Iceberg lakehouses.
Compaction runtime for Apache Iceberg.
Lakekeeper is an Apache-Licensed, secure, fast and easy to use Apache Iceberg REST Catalog written in Rust.
P2P Docker registry capable of distributing TBs of data in seconds
Create full-fledged APIs for slowly moving datasets without writing a single line of code.
Hourly Electricity Demand for different regions in US
Elkar - Task management for AI Agents, ready for Agent2Agent (A2A) protocol
An Open Standard for lineage metadata collection
Qbeast-spark: DataSource enabling multi-dimensional indexing and efficient data sampling. Big Data, free from the unnecessary!
Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers,…
Developed an end-to-end ML pipeline to predict truck delivery delays using real-world logistics data. Built modular data pipelines with PostgreSQL & MySQL, deployed a Streamlit app, and automated r…
This repository includes a benchmark and code for the paper "Evaluating LLMs at Detecting Errors in LLM Responses".
A task runner that works well with poetry or uv.
A kubernetes operator for managing nvidia MIG instances.
PDF DataSource for Apache Spark, allow to read PDF files directly to the DataFrame and ocr it
KubeStellar - a flexible solution for multi-cluster configuration management for edge, multi-cloud, and hybrid cloud
dbt-starrocks contains all of the code enabling dbt to work with StarRocks