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
superglue-ai/superglue
Superglue is a powerful platform designed to build production-grade integrations and tools from natural language inputs, targeting long-tail and enterprise systems. It acts as a lightweight proxy that can connect to any REST, GraphQL, SQL, Postgres, or file endpoint, enabling seamless integration with various data sources and APIs. One of its standout features is the use of large language models (LLMs) to assist in mapping data during configuration, which helps automate the generation of data transformations. These transformations are cached as JavaScript at runtime to avoid latency issues typically associated with LLMs. Superglue offers a self-healing mechanism for integrations, meaning that if an upstream API or schema changes, it automatically regenerates the necessary transforms to keep the integration running smoothly without manual intervention. Security is a priority, with zero data storage and options to run the platform fully on-premises or use their hosted cloud version. Users can choose between different modes: the superglue agent mode, which generates connectors for any API with OAuth support, and superglue toolkits, which provide pre-built and tested tools for AI agents. The platform supports flexible authentication methods, including header authentication, API keys, and OAuth, and handles various file formats such as CSV, JSON, and XML with automatic decompression. Additional features include smart pagination handling, schema validation to ensure data compliance, caching, and retry logic to enhance reliability. Superglue is ideal for enterprises looking to extend AI assistants or co-pilots with more actions, ship connectors faster without maintenance overhead, and simplify legacy API pipelines. It also supports transforming SQL queries into REST API calls, making it versatile for different integration needs. The project is open to contributions and provides detailed documentation and SDKs for easy adoption. It is licensed under GPL for the core platform and MIT for the client SDKs.
https://github.com/superglue-ai/superglue
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.