local.ai has been discontinued. Similar apps include Ollama, which is free and open source. Other options are Jan.ai, Ensu, GPT4ALL and Open WebUI. You're spoiled for choice with AI Chatbots like local.ai: we list more than 50 alternatives for Mac, Windows, Linux, Android and iPhone.
Access Apple’s local foundation model through a command-line tool with an OpenAI-compatible HTTP server, full function and schema calling, UNIX-friendly features, file attachments, JSON output, privacy-preserving on-device inference, and zero recurring costs.
Austria
EU
Leo is an AI-powered intelligent assistant, built right into the browser. Leo can answer questions, help accomplish tasks, and more.
United States
Ask questions to your documents without an internet connection, using the power of LLMs. 100% private, no data leaves your execution environment at any point. You can ingest documents and ask questions without an internet connection!
GermanyEU
Onit AI Copilot offers a comprehensive desktop AI chat assistant with local processing and multi-provider support. It prioritizes customization, extensibility, and user privacy by operating entirely on-device without needing an internet connection, ensuring data security.
United States
Deeply customizable virtual assistant offering flexible AI model support, voice chat, document interaction, web search, file and conversation management, extension integration, and a unified interface for organizing productivity and personal workflows.
OptiQ is an MLX-native toolkit for running large language models on Apple Silicon. No PyTorch, no CUDA, no cloud.
Tool for downloading AI and machine learning models from Hugging Face, Model Scope, and Civitai on Windows, featuring command line and GUI options, efficient management of large file downloads, integrity checks, and progress monitoring for users.
China
Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollama for decision models.
Custom Mac runtime allows instruction-tuned 26-billion-parameter model inference in about 2 GB RAM by streaming only required model experts from SSD, with 1.35 GB core and cache in memory. Supports 8 GB Apple Silicon Macs with CLI and native app, measured in 103 scenarios.
United Kingdom
KoboldCpp is an easy-to-use AI text-generation software for GGML models. It's a single self contained distributable from Concedo, that builds off llama.cpp, and adds a versatile Kobold API endpoint, additional format support, backward compatibility, as well as a fancy UI...
Run open-source LLMs on your computer. You can download and make custom characters for your models. Works offline. The new name is Back yard though it is the same.
ChatRTX is a locally-run AI chatbot developed by NVIDIA that leverages the power of RTX GPUs to deliver fast, private, and offline conversational AI. It uses models like Mistral or LLaMA and can be customized with your own documents and data.
United States
