AI Agent Platforms / All platforms / LlamaIndex
LlamaIndex
Python data framework for building agentic LLM applications over documents and data.
LlamaIndex is an open-source framework for building LLM applications that work over existing data. It provides data connectors, indexing, and retrieval interfaces, and is used by developers ranging from beginners using short high-level workflows to advanced users customizing lower-level APIs. A companion cloud product, LlamaParse, handles document parsing and extraction.
| Category | Agent builders and frameworks |
| License | MIT |
| Hosting | library for self-managed applications; vendor cloud available |
| Repository | github.com/run-llama/llama_index |
| Website | developers.llamaindex.ai/python/framework |
| Last verified | 2026-09-02 |
Documented features
- Ingests data from APIs, PDFs, documents, SQL, and other sources via data connectors
- Structures data as indices and graphs for use with LLMs
- Provides a retrieval and query interface that returns knowledge-augmented output
- Offers over 300 integration packages through LlamaHub for LLMs, embeddings, and vector stores
- Supports document agent workflows and multi-agent applications
- High-level API allows basic ingestion and querying in a few lines of code
- Lower-level APIs allow customization of connectors, indices, retrievers, and query engines
- LlamaParse cloud service adds parsing for 130+ formats and structured extraction
Feature summaries come from the project's own repository and documentation and describe the software as documented on the verification date, not an evaluation.