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
cocoindex-io/cocoindex
CoCoIndex is a robust data transformation framework designed for artificial intelligence applications, emphasizing high performance and incremental processing capabilities. It is engineered to handle large volumes of data efficiently, making it suitable for real-time applications. The framework supports change data capture (CDC) to enable continuous, update-driven data processing, which is crucial for maintaining up-to-date knowledge bases and contextual information for AI models. It facilitates data indexing, context engineering, and data processing, acting as a foundational layer for RAG (Retrieval Augmented Generation) systems and various AI agents. Built with a combination of Python and Rust, CoCoIndex leverages Rust's performance for critical operations while offering Python's flexibility for development and integration. This framework is particularly relevant for constructing long-horizon agents, AI agent ecosystems, and any system requiring dynamic, real-time access to semantic data. Its focus on incremental processing ensures that only changed data is processed, significantly reducing computational overhead and latency for AI applications like semantic search and knowledge graph construction.
https://github.com/cocoindex-io/cocoindex
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.
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.