TypeScript libraries that provide access to in-browser AI model providers with seamless fallback to using server-side models.
For detailed documentation, browser requirements and advanced usage, refer to the official documentation site.
| Package | AI SDK v5 | AI SDK v6 | AI SDK v7 |
|---|---|---|---|
@browser-ai/core |
✓ 1.0.0 |
✓ 2.x |
✓ ≥ 3.0.0 |
@browser-ai/transformers-js |
✓ 1.0.0 |
✓ 2.x |
✓ ≥ 3.0.0 |
@browser-ai/web-llm |
✓ 1.0.0 |
✓ 2.x |
✓ ≥ 3.0.0 |
# For Chrome/Edge built-in browser AI models
npm i @browser-ai/core
# For open-source models via WebLLM
npm i @browser-ai/web-llm
# For 🤗 Transformers.js models
npm i @browser-ai/transformers-jsimport { streamText } from "ai";
import { browserAI } from "@browser-ai/core";
const result = streamText({
model: browserAI(),
prompt: "Invent a new holiday and describe its traditions.",
});
for await (const chunk of result.textStream) {
console.log(chunk);
}import { streamText } from "ai";
import { webLLM } from "@browser-ai/web-llm";
const result = streamText({
model: webLLM("Llama-3.2-3B-Instruct-q4f16_1-MLC"),
prompt: "Invent a new holiday and describe its traditions.",
});
for await (const chunk of result.textStream) {
console.log(chunk);
}import { streamText } from "ai";
import { transformersJS } from "@browser-ai/transformers-js";
const result = streamText({
model: transformersJS("HuggingFaceTB/SmolLM2-360M-Instruct"),
prompt: "Invent a new holiday and describe its traditions.",
});
for await (const chunk of result.textStream) {
console.log(chunk);
}- Chrome for Developers: Use the Prompt API with the Vercel AI SDK
- Chrome for Developers: Use the Vercel AI SDK UI and AI Elements with the Prompt API
- Hugging Face: Building a Next.js application with the AI SDK
- Hugging Face: Transformers.js × Vercel AI SDK integration
- Huggingface Transformers.js AI SDK v5: next-vercel-ai-sdk-v5-transformers-js-example
- Huggingface Transformers.js AI SDK v6: next-vercel-ai-sdk-v6-transformers-js-example
This project is part of the Vercel OSS Program, and was previously sponsored by Chrome for Developers.
Contributions are more than welcome! However, please make sure to check out the contribution guidelines before contributing.
If you've ever built apps with local language models, you're likely familiar with the challenges: creating custom hooks, UI components and state management (lots of it), while also building complex integration layers to fall back to server-side models when compatibility is an issue.
Read more about this here.
2025 © Jakob Hoeg Mørk