Among 8 makers' products we track that are built with React, here's what they chose for AI SDK & agent framework — each counted from a live-product source.
Broad framework or thin SDK. Broad frameworks come with integrations for loaders, vector stores and memory, but add layers of abstraction you have to learn and debug. Thin SDKs give you a typed agent loop close to the raw API and leave the rest to you. An agent harness goes further the other way: the whole loop — file access, shell, context management — comes ready-made, for agents that work inside a workspace.
LangChain4
Mastra3
AI SDK1Counts are live products with a source, not market share; a product using two options counts in both.
LangChainBroad frameworkBest forThe largest set of ready-made integrations for models, tools and data sources, in Python and JavaScript.
Trade-offLayers of abstraction make debugging harder, and the API has changed often.
4 of the 8 React products here · free tier · open source
MastraTypeScript frameworkBest forTypeScript and Next.js apps that want agents, workflows, memory and RAG without a Python service.
Trade-offYounger ecosystem, and some enterprise features sit under a separate source-available license.
3 of the 8 React products here · free tier · open source
AI SDKThin SDKBest forTypeScript agents with tool calling, multi-step loops and streaming to the UI, on any model provider.
Trade-offMemory, workflows and evals are left to you or other libraries.
1 of the 8 React products here · free tier · open source
Also real options for AI SDK & agent framework, not seen among these React products yet: LlamaIndex, OpenAI Agents SDK, Pydantic AI, Claude Agent SDK, LangGraph.