pingcap/tidb
TiDB is an open-source, cloud-native, distributed SQL database offering ACID guarantees, horizontal scalability, high availability, HTAP capabilities, and MySQL compatibility.
Awesome AI Agents › Data Integration and Specialized Solutions
run-llama/llama_index
LlamaIndex is a comprehensive data framework designed to build applications powered by large language models (LLMs). It addresses the challenge of augmenting LLMs with private data by providing a robust toolkit that facilitates data ingestion, structuring, and querying. The framework offers data connectors to ingest various data sources and formats such as APIs, PDFs, documents, and SQL databases. It enables users to structure their data into indices and graphs, making it easier to utilize with LLMs. LlamaIndex also features an advanced retrieval and query interface that allows feeding any LLM input prompt and receiving contextually relevant, knowledge-augmented output. The framework supports seamless integration with external application frameworks like LangChain, Flask, Docker, and ChatGPT, enhancing its versatility. LlamaIndex caters to both beginners and advanced users. Beginners can quickly ingest and query data with minimal code, while advanced users have access to lower-level APIs to customize and extend modules such as data connectors, indices, retrievers, query engines, and reranking modules. The project is modular, with a core package and over 300 integration packages available on LlamaHub, allowing users to tailor their setup with preferred LLMs, embedding models, and vector stores. The project is actively maintained and supported by a community, with resources including documentation, examples, and a contribution guide. It also has a TypeScript/JavaScript version and a community library of data loaders called LlamaHub. LlamaIndex is positioned as a leading framework for building LLM-powered agents that leverage private and external data sources effectively, making it a valuable tool for developers working on AI applications that require enhanced data interaction and retrieval capabilities.
https://github.com/run-llama/llama_index
Also in Data Integration and Specialized Solutions
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.
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.