Product / UX / Orchestration & agents

LlamaIndex

Open-source data framework (Python and TypeScript) for building LLM apps over private data: data connectors, indexing/retrieval, and an agent/Workflows orchestration layer. Its depth is in RAG and data ingestion - 'document agents', many-format parsing, and structured extraction.

MIT core; commercial LlamaCloud / LlamaParse (parse/extract/index APIs) makes the overall offering open-core. ~50k stars, ~10M PyPI downloads/month.

Openness

4 high confidence

4.0

license: MIT(core)
commercial: LlamaCloud/LlamaParse
source: public

MIT self-hostable core with a commercial managed cloud.

https://github.com/run-llama/llama_index recorded 2026-06-17
MIT, ~50.2k stars, LlamaCloud commercial tier

Adoption

5 high confidence

5.0

~10.18M PyPI downloads/month.

https://pypistats.org/packages/llama-index recorded 2026-06-17
~10.18M downloads/month

Capability

5 high confidence

5.0

Best-in-class RAG/data-ingestion depth plus an agent layer.

https://github.com/run-llama/llama_index recorded 2026-06-17
feature set: connectors, indices, Workflows, extraction

Unchanged since 2026-06-17 (last edited, not re-checked)