Skip the hype. Find AI software for your next project.

Run and build with open AI models locally or in the cloud

Google's family of lightweight, open-weight AI models

Own your intelligence: a private AI assistant that runs entirely on your machine

Self-hosted AI workspace for local and cloud models

Open-source desktop AI that runs models locally on your own machine

Open-source, memory-efficient fine-tuning and local model running

Native macOS inference server that makes local LLMs instant for coding agents

Check which local AI models your GPU or Mac can actually run

Run local AI for text, images and speech on your own machine

Run open-source LLMs locally on your own laptop, fully offline

Alibaba Cloud's 4th-generation multimodal AI assistant and foundation model lineup (Qwen4-Max, Qwen4-Plus, Qwen4-Flash & open-weight Qwen4-27B) with 1M context.

Google's multimodal AI assistant powered by Gemini 4 Carbon (Gemini Carbon 4), Gemini 4 Argon, and Gemini 3.8 Flash with a 1M-token context window and Workspace integration.

High-efficiency open-weight and hosted reasoning AI powered by DeepSeek-V4 and R1 at ultra-low token costs.

Enterprise developer platform and API for deploying GPT-6 Astra, Sol, Luna, and realtime multimodal agents.

Run AI models offline with a free, open-source desktop playground

Embed private generative AI, RAG and agents directly inside your .NET application

One native Mac workspace for hundreds of AI models

Google's rapid prototyping IDE and developer API workbench for building multimodal applications with Gemini models.

One workspace for Claude, GPT, Gemini, Grok and more

A private, memory-powered AI assistant you own and customize

Open-source multi-model AI desktop workspace

The fast, private desktop chatbot for every major LLM

The best frontend for AI.

Private AI for real work — workspaces, agents, models, and knowledge on your terms