Report card

Do AI agents pick LlamaIndex?

How often agents choose LlamaIndex when a developer needs ai sdk — measured across Claude, GPT, Gemini.

LlamaIndex

#4 of 5 ai sdk
1%Pick Rate
95% CI 0%3%

When developers ask an AI agent for ai sdk, LlamaIndex is picked 1% of the time — ranking #4 of 5 measured across Claude, GPT, Gemini.

Picked 1% Named, not picked 13% Never surfaced 86%

Beaten by OpenAI SDK (51%), Vercel AI SDK (14%), LangChain (5%).

Awareness

0 docs in FineWeb (10BT sample) · 556 URLs in Common Crawl

In the raw web crawl, but thin in the filtered corpus models actually train on — an awareness gap at the source.

AdoptionDid the pick convert to installs? Public Adoption = npm downloads of your packages. The proof half of the funnel.

461K installs / month ▲ 8% MoM

Installs are roughly flat month over month.

Get the full report

The per-model and per-surface breakdown for LlamaIndex — where it wins, where it loses, and to whom — plus an alert when the Pick Rate moves.

About LlamaIndex

A data framework for building LLM applications with your own data in TypeScript.

LlamaIndex is a framework that lets developers connect their own data sources to large language models like OpenAI, Anthropic, Gemini, and others. It handles data ingestion, indexing, and querying so applications can retrieve and reason over custom data. It targets TypeScript developers building LLM-powered apps across Node.js, Deno, Bun, Vercel Edge, and Cloudflare Workers.

Where to start

Install the core package and the relevant provider package for your chosen LLM (for example, @llamaindex/openai for OpenAI), then follow the getting started guide in the official documentation at ts.llamaindex.ai.

Install

Links and summary verified from public sources.

The rest of the AI SDK ranking

← Full AI SDK leaderboard · How this is measured