Dendrite SDKIn-Browser AI Chat

Run LLM personas entirely in the browser. WebGPU where it works, WASM where it doesn't.

Zero Server (by default)

Models run directly in the visitor's browser via WebGPU or WASM. No API keys, no backend, no data leaves the device.

Auto Fallback

Picks the fastest engine available — WebLLM on WebGPU, Transformers.js on WASM, or an optional cloud proxy if you want one.

Personality System

Shape LLM behavior with typed documents — zero-shot identity, personality, knowledge, and instruction docs.

Framework Agnostic

Pure TypeScript core. Drop-in Vue components in @agent-layer-zero/dendrite-vue, React in @agent-layer-zero/dendrite-react, or framework-agnostic Web Components in @agent-layer-zero/dendrite-ui for everywhere else (Svelte, Astro, vanilla HTML).

Streaming

Async generator API streams tokens as they're generated. Build responsive chat UIs with real-time output.

Sibling Packages

Looking for prebuilt UI? See the Framework Packages guide for dendrite-vue, dendrite-react, dendrite-ui, and soma (shared CSS).