Do AI agents pick LangChain?
How often agents choose LangChain when a developer needs ai sdk — measured across Claude, GPT, Gemini.
95% CI 3%–9%
When developers ask an AI agent for ai sdk, LangChain is picked 5% of the time — ranking #3 of 5 measured across Claude, GPT, Gemini.
0 docs in FineWeb · 273 URLs in Common Crawl
40.6M installs / month ▲ 4% MoM
Get the full report
The per-model and per-surface breakdown for LangChain — where it wins, where it loses, and to whom — plus an alert when the Pick Rate moves.
About LangChain
A framework for building applications powered by large language models.
LangChain gives developers a standard interface for connecting LLMs to data sources, tools, vector stores, and external systems through interoperable, swappable components. It targets developers building AI-powered applications who need to work across multiple model providers or integrate retrieval, agents, and other LLM patterns without tightly coupling to any one vendor. The broader ecosystem includes LangGraph for agent orchestration and LangSmith for testing and monitoring LLM apps in production.
Where to start
Install the `langchain` package via npm, pnpm, or yarn, then follow the official getting-started documentation which covers environment setup and simple working examples. For agent-based or more complex workflows, the LangGraph.js documentation is the recommended next step.
The rest of the AI SDK ranking
| 1 | OpenAI SDK | 51% |
| 2 | Vercel AI SDK | 14% |
| 4 | LlamaIndex | 1% |
| 5 | Anthropic SDK | 0% |