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
electric-sql/electric
Electric is a robust Postgres sync engine designed to simplify real-time data synchronization for applications and AI agents. It addresses complex synchronization challenges such as partial replication, fan-out, and efficient data delivery. The core of Electric is based on a low-level HTTP API, which intelligently integrates with CDNs to facilitate highly scalable data delivery. One of its key features is 'Shapes,' which manages partial replication, allowing developers to define specific subsets of data to be synchronized. This ensures that only relevant data is moved, optimizing performance and resource usage. Electric can be consumed directly through its API or via client libraries and framework integrations, offering flexibility in how developers interact with the synchronized data. The project provides comprehensive documentation, quickstart guides, and examples to help users get started rapidly. It also includes an optional Phoenix LiveDashboard for real-time monitoring of system metrics, and it supports development using `asdf` for managing Elixir, Erlang, and Node.js environments. Designed to free developers from the complexities of building custom sync solutions, Electric empowers them to focus on crafting fast, modern software applications and AI agents that operate on live, up-to-date data.
https://github.com/electric-sql/electric
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.