- fix: resolve a ton of security alerts
- fix: resolve a ton of security alerts
- fix: resolve a ton of security alerts
- fix: resolve a ton of security alerts
- fix: resolve a ton of security alerts
- fix: resolve a ton of security alerts
LlamaIndex by LlamaIndex
Overview
A framework for building LLM applications and agents over your own data, covering document processing, retrieval and agent workflows.
LlamaIndex was downloaded 848K times from npm and PyPI in the week ending Oct 4, 2026, up 2.6% on the week before and down 48.0% over the last 30 days compared with the 30 before. The GitHub repository has 52.4K stars, 455 of them added in the last 30 days. The latest stable release is 0.14.25, published Sep 21, 2026; there were 1 stable releases in the past 30 days. It was mentioned in 10 Hacker News posts and comments over the last 30 days.
LlamaIndex usage and attention over time
Download the raw daily series: llamaindex.csv
Install LlamaIndex
| npm | npm install llamaindex |
|---|---|
| PyPI | pip install llama-index |
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Key facts
| Maker | LlamaIndex |
|---|---|
| Type | Data and agent framework |
| License | MIT |
| Interfaces | Python library, TypeScript library |
| Main language | Python |
| Open issues and PRs | 893 |
Pricing
The LlamaIndex framework is open source and free. The company sells separate hosted services for document parsing and indexing.
Source: official pricing page, checked Oct 5, 2026. Prices change often; confirm before you buy.
Pulse Score breakdown
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
What changed: recent LlamaIndex releases
2 stable releases in the last 90 days · Full changelog
- fix: close HotpotQA evaluator file handles
- fix(core): preserve oversized leaf nodes in CodeSplitter
- fix: preserve multiblock chat history writes
- fix(core): skip empty nodes in HTMLNodeParser
- fix(core): respect mmrthreshold=0 in MMR embedding search
- fix: keep all nodes per document in IngestionPipeline upserts (re-submit of #22046, not a dup of #21456)
- chore(deps): bump the uv group across 32 directories with 3 updates
- chore(deps): bump the uv group across 29 directories with 3 updates
- chore(deps): bump the uv group across 31 directories with 3 updates
- chore(deps): bump the pip group across 35 directories with 4 updates
- chore(deps): bump the uv group across 32 directories with 5 updates
- chore(deps): bump the uv group across 31 directories with 5 updates
- mass uv lock --upgrade
- chore(deps): bump the pip group across 55 directories with 3 updates
- mass uv lock --upgrade
- mass uv lock --upgrade
- chore(deps): bump the pip group across 55 directories with 3 updates
- chore(deps): bump the pip group across 55 directories with 3 updates
- chore(deps): bump the pip group across 87 directories with 2 updates
- chore(deps): bump the pip group across 68 directories with 2 updates
- fix(core): prevent KeyError in DocumentSummaryIndex.deletenodes when invalid node ID is provided
- fix(core): handle ValueError and TypeError from structured output failures
- fix: add explicit UTF-8 encoding to persistence layer fs.open() calls
- Fix Breaking Change in Message Block Buffer Resolution
- fix vulnerability with nltk
- chore(deps): bump the uv group across 50 directories with 2 updates
- chore(deps): bump the uv group across 24 directories with 1 update
- chore(deps): bump the uv group across 21 directories with 2 updates
- fix vulnerability with nltk
- fix vulnerability with nltk
LlamaIndex alternatives
| # | Agent | Pulse | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | Last 90 days | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 4 |
LangChainLangChain |
77 | 44.3M | up 1.9% | down 22.0% | — | 147K+45/day | 1.4.38d ago | Free (OSS) | ||
| 10 |
LangGraphLangChain |
69 | 16.1M | up 11.4% | down 21.8% | — | 42.7K+48/day | 1.2.13yesterday | Free (OSS) | ||
| 11 |
AI SDKVercel |
67 | 34.5M | up 13.5% | up 20.9% | — | 27.1K+18/day | 6.0.301yesterday | Free (OSS) | ||
| 13 | 63 | 8.7M | up 0.6% | up 2.0% | — | 8,679+23/day | 1.58.0yesterday | Free (OSS) | |||
| 17 |
Claude Agent SDKAnthropic |
59 | 21.5M | up 14.6% | up 0.6% | — | 8,219+5/day | 0.2.1636d ago | Free (OSS) | ||
| 21 |
MastraMastra |
58 | 2.2M | up 11.1% | up 19.1% | — | 28.6K+27/day | 1.74.0yesterday | Free (OSS) | ||
| No agents match that filter. | |||||||||||
LlamaIndex FAQ
How much does LlamaIndex cost?
The LlamaIndex framework is open source and free. The company sells separate hosted services for document parsing and indexing.
Is LlamaIndex open source?
Yes. LlamaIndex is open source, released under the MIT license.
How popular is LlamaIndex?
LlamaIndex was downloaded 848K times from npm and PyPI in the week ending Oct 4, 2026, up 2.6% on the week before and down 48.0% over the last 30 days compared with the 30 before. The GitHub repository has 52.4K stars, 455 of them added in the last 30 days. The latest stable release is 0.14.25, published Sep 21, 2026; there were 1 stable releases in the past 30 days.
What is the latest version of LlamaIndex?
The latest stable release we track is 0.14.25, published on Sep 21, 2026.
What are the alternatives to LlamaIndex?
The closest alternatives in the same category by Pulse Score are LangChain, LangGraph, AI SDK, Strands Agents.
Where these numbers come from
npm: llamaindex. PyPI: llama-index. GitHub: run-llama/llama_index. See data sources for how each one is collected.
