Open Source, Personal Desktop AI Assistant for Linux, Windows, and Mac with Chat, Vision, Agents, Image and Video generation, Tools, Voice control and more.
Supports multiple models: GPT-5, GPT-4, o1, o3, o4, Sora2, and more, as well as non-OpenAI models like Google Gemini, Anthropic Claude, xAI Grok, Perplexity Sonar, DeepSeek, Mistral AI, and any models provided by Ollama and LlamaIndex.
Includes a model editor and importer.
Multiple modes of operation: Chat for natural conversation, Chat with Files for utilizing local files as additional context, Vision for image and camera-capture analysis, Agents for handling complex and autonomous tasks, Audio for audio-based interactions, Research for in-depth exploration using Perplexity and OpenAI's advanced research models, Computer Use, and more.
Execute system and custom commands, generate and run Python code, and connect to any service—including web access. Handle various file types and data sources, automate tasks, and enhance productivity with local and external tools integrated into your workflow.
Free and open-source
Source code is available on GitHub.
build 2026-02-06, 64-bit
Binaries (Windows 10/11, Linux):