#55th of 9 in Agent frameworks and SDKs
llama_index
Python framework for RAG and agent apps over your own data
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 52.5k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Python
47,478 on 24 Mar 202652,483 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
LlamaIndex is a Python toolkit that loads data from files, APIs and SQL, builds indices such as a vector store index, and exposes query engines and retrievers for LLM apps. The llama-index-core package is extended by over 300 integration packages for LLMs, embeddings and vector stores. The maintainers say their main focus has moved to the commercial LlamaParse platform, while the framework stays available as open source.
Who it is for: Python developers building RAG or agent apps over private documents
Strengths
- Over 300 integration packages for LLM, embedding and vector store providers
- Small core package plus a starter bundle; install only the integrations needed
- High-level API indexes and queries a directory in a few lines
- Works with local models, e.g. Ollama LLMs and Hugging Face embeddings
Weaknesses
- README says company focus has shifted to the paid LlamaParse platform
- README is noted as less up to date than the documentation
- Index storage is in-memory by default; persistence to ./storage is manual
- Library only: no UI, server or Docker setup included
What it needs
- GPU optional
- Needs Python, LLM provider API key or local Ollama, LlamaParse account (optional)
- Models: OpenAI, Ollama, Hugging Face embeddings
Also in Agent frameworks and SDKs
See all 9| Rank | Project | Score |
|---|---|---|
| 1 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| 2 | browser-usePython library that lets an LLM agent control a web browser | 87 out of 100 |
| 3 | crewaiPython framework for multi-agent workflows with role-based Crews and event-driven Flows | 77 out of 100 |
| #4 | agnoPython SDK and runtime for building and serving agents behind a REST API | 69 out of 100 |
| #6 | langgraphPython framework for building long-running, stateful agents as graphs | 66 out of 100 |