LlamaIndex
LlamaIndex by LlamaIndex: what it does, how it works, pricing and adoption — sourced and dated.
Agent frameworks Open source · MIT ≈52.3K GitHub stars (2026-09)
LlamaIndex is the leading framework for building LLM applications over your own data — indexing, retrieval and RAG first, with agent workflows on top. At roughly 52,300 GitHub stars it is one of the most-adopted projects in this section; its company monetises LlamaCloud, the managed parsing/indexing service, while the framework itself stays MIT.
How it works
The data-first framework: agents are built over your indexed data with retrieval, and its Workflows layer orchestrates event-driven agent steps. Choose it when the agent's hard problem is your documents, not the chat loop.
The facts
| Maker | LlamaIndex |
| Type | Agent framework |
| Category | Agent frameworks |
| Status | Active |
| License | MIT |
| Models | Model-agnostic; 300+ data connectors feed its indexes. |
| GitHub stars | 52,300 (snapshot 2026-09) |
| Website | https://www.llamaindex.ai |
Pricing
Framework is free and open source (MIT). The hosted companion, LlamaCloud (managed parsing and indexing), has a free tier, then Starter at $50/month.
Pricing model: Free / open source (+ paid cloud) · Source: published tiers · checked Oct 14, 2026
Frameworks run on models — compare them in the model database or check the price comparison before you build.
Also in Agent frameworks
- LangGraph — LangChain
- CrewAI — CrewAI
- AutoGen — Microsoft
- Microsoft Agent Framework — Microsoft
- OpenAI Agents SDK — OpenAI
- Strands Agents — AWS
Sources
Profile verified Oct 14, 2026. Spotted an error? Every figure above links to its source.