py-gpt
Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - chat, agents, tools, MCP, plugins, RAG, vision, voi
What is py-gpt?
Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - chat, agents, tools, MCP, plugins, RAG, vision, voice, image and video generation, speech synthesis and speech recognition, web search, memory, presets, canvas, assistants, themes, computer use. Windows, Linux, and Mac.
Overview of py-gpt
What it is
PyGPT is an open-source desktop AI assistant for Linux, Windows, and macOS. It supports models from OpenAI (GPT-6 Astra, GPT-5.6, GPT-4, etc.), Google Gemini, Anthropic Claude, xAI Grok, Perplexity/Sonar, DeepSeek, plus models through HuggingFace, LlamaIndex, OpenAI-compatible APIs, and local Ollama installations (DeepSeek, Qwen, gpt-oss, Gemma, Mistral, Llama, and others). It includes chat, agents, tools, MCP, plugins, RAG, vision, voice, image and video generation, speech synthesis and recognition, web search, memory, presets, canvas, assistants, themes, and computer use.
Key features
- Desktop AI assistant for Linux, Windows, and macOS with a ChatGPT-like interface.
- Supports multiple AI models: OpenAI GPT-6 Astra, GPT-5.6, GPT-4, Google Gemini, Anthropic Claude, xAI Grok, DeepSeek V3/R1, Perplexity/Sonar, and models via LlamaIndex and Ollama.
- Integrated LlamaIndex RAG for files, webpages, Google/GitHub data, media, images, conversation history, and formats such as txt, pdf, csv, html, md, docx, json, epub, xlsx, and xml.
- Image generation with models like gpt-image, Imagen, Gemini, and Nano Banana; video generation with Veo3 and Sora2.
- Web search via DuckDuckGo, Google, Microsoft Bing, and remote web search.
- Speech synthesis via OpenAI, Microsoft Azure, Google Cloud/GenAI, Eleven Labs, and xAI; speech recognition via OpenAI Whisper (API or local), Google/Google Cloud/GenAI, Microsoft Bing, and xAI Grok Voice.
- Extensible plugin system with Filesystem, Python and OS, Web search, Google, Facebook, X/Twitter, Slack, Telegram, GitHub, MCP, and more; includes Model Context Protocol (MCP) support and MCP Connectors manager.
Use cases
PyGPT can be used for conversational chat, multi-agent workflows (Chat, Orchestrator, Swarm), research, text completion, image and video generation, computer use, autonomous mode, custom agents, realtime audio interaction, file analysis with RAG, web search, voice input/output, automation via plugins and MCP, and integration with external services like Google, GitHub, Slack, and Telegram.
Getting started
Install via pip: bash pip install pygpt Or via Snap: bash sudo snap install pygpt For prebuilt binaries (Windows/Linux), AppImage, Microsoft Store, or source installation, see the repository README.
License and pricing
Open source (no specific license identifier). Free.
Based on the project's public README and repository metadata.
