LocalMode.AI

LangChain.js adapters for @localmode — drop-in local inference for existing LangChain apps

Cross-browser storage adapter with automatic fallback using localforage

WebLLM provider for @localmode - LLM inference with quantized models

wllama provider for @localmode - GGUF model inference via llama.cpp WASM with metadata inspection and browser compatibility checking

Vercel AI SDK provider for @localmode - use local models with generateText, streamText, and embed

Cross-runtime benchmark harness for in-browser AI — MLPerf-Client-compatible metrics (TTFT, prefill/decode throughput), raw trace capture, integrity checks, and leaderboard aggregation for LLM and embedding inference across browser ML runtimes

Local-first AI utilities for the browser. Zero dependencies. Privacy-first.