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
Canner/vulcan-sql
VulcanSQL is an Analytical Data API Framework designed to simplify and secure the process of delivering RESTful APIs from various data sources such as databases, data warehouses, and data lakes. It is particularly aimed at enabling AI agents and data applications to interact seamlessly with analytical data. The framework addresses common challenges faced by data professionals and developers, including the time-consuming and error-prone nature of custom API development, integration complexities with diverse data sources, security and compliance concerns, scalability and performance issues, and the lack of standardized documentation and usability. VulcanSQL streamlines API creation by abstracting the complexities of direct database interactions, allowing developers to focus on application logic rather than low-level data handling. It supports rapid development and integration, standardizes API interactions through OpenAPI documents, and offers a template-driven approach that facilitates scalability and easier maintenance. The framework also enhances accessibility by making data more available to AI agents, unlocking new insights and enabling automation. Key features include a development experience similar to dbt, where SQL templates can be dynamically generated based on API inputs, and the use of DuckDB as a caching layer to accelerate query performance and reduce API response times. VulcanSQL supports flexible deployment options, including Docker and command-line setups, and provides tools for packaging and sharing data APIs. It integrates well with internal tools and supports various use cases such as AI agent interaction, customer-facing analytics, secure data sharing, and internal tool integration. The project offers comprehensive documentation covering installation, API building, data source connections, caching, error handling, validation, data privacy, extensions, and deployment. An online playground and example repositories are available to help users get started and explore practical applications. VulcanSQL is maintained by Canner and is actively supported through community channels like GitHub issues and social media.
https://github.com/Canner/vulcan-sql
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.
cube-js/cube
Cube Core is an open-source semantic layer that enables AI, business intelligence, and embedded analytics by providing a flexible, API-driven platform supporting multiple SQL data sources and real-time analytics.
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.