PyGPT
Open-source desktop AI assistant with 12 modes, multi-model support, and plugin system
About PyGPT
PyGPT is a free, open-source desktop AI assistant for Windows, macOS, and Linux that supports 12 operational modes including chat, vision, agents, autonomous mode, image/video generation, voice control, and computer use. It connects to multiple AI providers — OpenAI (GPT-5, GPT-4, o1, o3), Google Gemini, Anthropic Claude, xAI Grok, DeepSeek, Perplexity, Mistral, and local models via Ollama. PyGPT includes built-in RAG with vector database support for chatting with documents (PDF, CSV, DOCX, and more), 20+ plugins, Python code execution, system command integration, speech synthesis/recognition, web search, long-term memory, and accessibility features for users with disabilities.
Pros & Cons
Pros
- Completely free and open-source (MIT license) with no premium tiers
- Supports virtually every major AI model provider in one app
- 12 distinct operational modes for different use cases
- Powerful RAG with built-in vector database for document chat
- Available on all desktop platforms (Windows, macOS, Linux)
- Active development with frequent updates (latest: v2.7.12)
Cons
- Requires users to provide their own API keys for each service
- Desktop-only — no web or mobile version available
- Can be overwhelming with 12 modes and 20+ plugins for new users
- UI is functional but not as polished as commercial alternatives
- API costs from providers (OpenAI, etc.) are the user's responsibility
Key Features
12 Operational Modes
Chat, Chat with Files, Realtime Audio, Research (Perplexity), Completion, Image/Video Generation, Vision, Assistants, Experts, Computer Use, Agents, and Autonomous Mode
Multi-Model Support
Works with OpenAI GPT-5/4/o1/o3, Google Gemini, Anthropic Claude, xAI Grok, DeepSeek, Perplexity, Mistral, and local models via Ollama
RAG & Document Chat
Chat with your data — supports PDF, CSV, DOCX, HTML, JSON, EPUB, XLSX, XML, webpages, GitHub repos, video, audio, and images via LlamaIndex
Code Execution
Generate and run Python code, execute system commands, and manage file operations directly from the assistant
Voice Control
Speech synthesis via Azure, Google, ElevenLabs, and OpenAI TTS, plus speech recognition for hands-free operation
Image & Video Generation
Create images with DALL-E and videos with Sora 2 and Veo 3 directly from the chat interface
Plugin Architecture
20+ built-in plugins with extensible architecture for adding custom functionality and tools
Accessibility Features
Customizable keyboard shortcuts, voice control, and on-screen action translation to audio for users with disabilities
Pricing
- All features included (MIT license)
- 12 operational modes
- Multi-model support (OpenAI, Gemini, Claude, Grok, etc.)
- 20+ built-in plugins
- RAG with vector database support
- Voice control and speech synthesis
- Image and video generation
- Bring your own API keys