Alternatives to Nexa SDK

Open-weight on-device AI models for private, low-latency edge intelligence

Free, privacy-first on-device text-to-speech for developers

Offline-first Kotlin Multiplatform library and app for private on-device LLM, STT, and image generation.

Tether's local AI SDK: run LLMs, vision, and voice entirely on-device, cross-platform.

Free on-device AI model zoo: 57 Core AI models with recipes and one-line Swift loading.

On-device Mac autocomplete that predicts your next words inline, privately.

Official 1-bit LLM inference framework for lossless CPU/GPU inference

Run open-source models locally or connect online APIs in one free desktop app

Run open-source LLMs locally with one command, then scale to the cloud

Free local RAG chatbot for RTX GPUs – private document Q&A on your PC

Run local LLMs offline with LM Studio's Bionic agent

Free offline AI chat with 1000+ local LLMs, no account needed.

Open-source framework for self-hosted RAG with Zero data leaks.

Run any GGUF AI model locally on Android with zero network permissions

Distributed LLM inference across any GPUs – run bigger models without buying bigger hardware.

Run large language models at home, BitTorrent-style decentralized inference

Free, offline local AI server for Apple Silicon Macs—fast inference, creative tools, and agent mode.

Open-source local AI runtime: text, voice, vision, images, video, agents.

Fastest MLX inference engine for Apple Silicon with prefix caching, batching, and MCP.

100% offline AI assistant for Android & iOS with 15+ local models

Open-source AI companion that recreates past conversations from your local chat logs using RAG.

Open-source desktop app for running RWKV RNN LLMs locally with infinite context.

Local, private AI autocomplete for every Mac app you type in.

Run open-source AI models fully offline on iPhone and Mac — private by design.

Open-source desktop hub for multiple AI models, offline and private.

Run LLMs in-browser with WebGPU — headless React hooks, just useLLM().

Run local LLMs in your browser with zero infrastructure cost.

AI-enhanced instant messaging with multi-LLM support and modular architecture.

Self-hosted AI gateway for local GGUF models, cloud APIs, and MCP tools with enterprise auth.

Fast native macOS ChatGPT client with built-in API key and tabbed chats.