Alternatives to Mirai

Free, MIT-licensed local LLM inference for Apple Silicon Macs, with SSD-backed prefix caching and native OpenAI and Anthropic APIs.

Fastest offline AI server for Apple Silicon: local LLMs, images, music, video, 3D.

Microsoft's open-source framework for running 1-bit LLMs with fast, lossless CPU/GPU inference

On-device GenAI SDK for Qualcomm Snapdragon, now part of Qualcomm AI Hub.

100% offline AI assistant for Android & iOS with 15+ on-device models.

Open-weight on-device AI with native audio, vision, and Japanese models, free under $10M revenue.

Run classic After Dark screen savers on modern macOS with Afterglow

Free on-device text-to-speech model you run locally through ONNX Runtime, no cloud round-trip and no per-character bill.

Private on-device LLM, speech-to-text, and image generation for Kotlin Multiplatform.

Run AI locally on any device with Tether's decentralized, cross-platform SDK for LLMs, voice, and vision.

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

ChatTab is a native macOS ChatGPT client with tabs, global shortcuts, and pay-as-you-go access.

Run open models locally or in the cloud with one command — then plug them into Claude Code, Codex, and other coding agents.

Run 123+ open-source models locally or connect online APIs in one free, open-source desktop app

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

Run private local AI agents with LM Studio Bionic

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

Run large language models at home by joining a BitTorrent-style network that serves the rest of the model for you

Free local AI chat running 1000+ open-source models fully offline.

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

Open-source framework for building private, on-premise RAG applications with 100% local data control.

Split big LLMs across your GPUs and run them locally with one OpenAI-compatible API.

Open-source, local-first AI client for private, multi-model conversations.

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

Open-source Kubernetes operator for deploying and scaling LLMs, embeddings, and speech-to-text with intelligent autoscaling.

Open-source local AI runtime: text, voice, vision, images, 3D, agents, on your hardware.

AI autocomplete that works everywhere you type on Mac

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

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

Free desktop AI that runs the Mistral 7B model locally so your documents never leave your machine.