New:Introducing Socket Scanning for VS Code Marketplace Extensions.Learn more →
Get Started
l

localmode

npm

386

total weekly downloads

Packages

Current Co-maintainers

Former Co-maintainers

16 packages

@localmode/ai-sdk

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

@localmode/bench

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

@localmode/chrome-ai

Chrome AI provider for @localmode - on-device inference via Chrome's built-in Gemini Nano

@localmode/core

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

@localmode/devtools

DevTools instrumentation and React hooks for debugging and monitoring LocalMode applications

@localmode/dexie

Dexie.js storage adapter for @localmode - enhanced IndexedDB with versioning

@localmode/idb

Minimal IndexedDB storage adapter using the idb library

@localmode/langchain

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

@localmode/litert

LiteRT-LM provider for @localmode - Google's on-device LLM inference engine with WebGPU/CPU support, runs .litertlm models (Gemma 4, Qwen3)

@localmode/localforage

Cross-browser storage adapter with automatic fallback using localforage

@localmode/mediapipe

MediaPipe Tasks provider for @localmode - hand/pose/face landmarks, gesture recognition, audio classification, language detection, and more via Google's on-device WASM runtime

@localmode/pdfjs

PDF text extraction for @localmode using PDF.js

@localmode/react

React hooks for @localmode — useChat, useEmbed, useClassify, and more

@localmode/transformers

Transformers.js provider for @localmode - implements all ML model interfaces

@localmode/webllm

WebLLM provider for @localmode - LLM inference with quantized models

@localmode/wllama

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