run-llama/llama_index
LlamaIndex is a leading data framework that enables building LLM-powered applications by providing tools for data ingestion, structuring, and advanced querying to augment large language models with private and external data.
Awesome AI Agents › Data Integration and Specialized Solutions
cube-js/cube
Cube Core is an open-source semantic layer designed for AI, business intelligence (BI), and embedded analytics. It serves as a foundational engine that defines metrics, dimensions, and business logic while abstracting the complexities of underlying data sources. Unlike proprietary semantic layers tied to specific BI platforms, Cube Core is decoupled and accessible through multiple APIs including REST, GraphQL, and SQL, enabling its use across various analytics applications and AI agents. This flexibility allows organizations to define their metrics once and reuse them everywhere, from BI tools to embedded analytics and AI-driven insights. Cube Core supports all SQL data sources, including cloud data warehouses like Snowflake, Databricks, and BigQuery, query engines such as Presto and Amazon Athena, and traditional application databases like Postgres. It features a built-in relational caching engine that ensures sub-second latency and high concurrency for API requests, making it suitable for real-time analytics needs. The project is designed to be headless, providing a semantic layer without a user interface, which allows developers to build custom analytics solutions or integrate analytics into existing applications seamlessly. Cube Core can be run locally or self-hosted using Docker, facilitating easy setup and deployment. Cube Core is the core engine behind Cube, a modern AI-first business intelligence platform that offers a fully integrated solution with a user-friendly interface and advanced analytics capabilities. The open-source nature of Cube Core encourages community contributions, issue reporting, and collaborative development, with extensive documentation, examples, and tutorials available to help users get started and extend its functionality. Overall, Cube Core aims to democratize access to semantic layers by providing an open, modern, and flexible solution that supports a wide range of data sources and analytics use cases, empowering organizations to leverage their data effectively for business intelligence and AI applications.
https://github.com/cube-js/cube
Also in Data Integration and Specialized Solutions
pingcap/tidb
TiDB is an open-source, cloud-native, distributed SQL database offering ACID guarantees, horizontal scalability, high availability, HTAP capabilities, and MySQL compatibility.
getzep/graphiti
Graphiti is a framework for building and querying real-time, temporally-aware knowledge graphs designed to support AI agents in dynamic environments with efficient incremental updates and hybrid retrieval methods.
dolthub/dolt
Dolt is a SQL database with Git-like features, enabling full version control over data, including branching, merging, and diffing of data.
vectordotdev/vector
Vector is a high-performance, end-to-end observability data pipeline designed to collect, transform, and route logs, metrics, and traces.
llmware-ai/llmware
llmware is a unified framework for building enterprise Retrieval-Augmented Generation (RAG) pipelines using small, specialized language models integrated with secure knowledge sources for efficient AI applications.
cocoindex-io/cocoindex
CoCoIndex is an ultra-performant data transformation framework for AI, specializing in incremental processing for data indexing and real-time semantic search with Python and Rust.
electric-sql/electric
Electric is a Postgres sync engine that provides real-time data synchronization, partial replication, and data delivery for modern applications and AI agents.