LlamaIndex · Framework for Document Agents and RAG
An open-source framework for building document-grounded AI agents and retrieval-augmented generation pipelines.
Best for
Document-grounded agents and retrieval-augmented generation
Not ideal for
General-purpose agent orchestration without a document/data focus
Who it's for
Developers building AI applications grounded in documents, databases, and private data sources
LlamaIndex is a framework for building AI applications grounded in your own data — documents, PDFs, databases, and APIs. It provides tools for document parsing, indexing, retrieval, and agent orchestration, enabling developers to build retrieval-augmented generation (RAG) pipelines and document-aware agents. The open-source Python library handles data ingestion, chunking, embedding, and retrieval. LlamaIndex also offers a cloud service (LlamaCloud) with managed document parsing (LlamaParse), agentic OCR, and hosted deployment — with a free tier of 10,000 credits per month. The framework is used by developers building knowledge-grounded chatbots, document Q&A systems, research tools, and structured data extraction pipelines. Deployment options include running the open-source library in your own infrastructure or using LlamaCloud for managed hosting and VPC deployment.
Are you the founder? Claim this listing →