PyGPT is an open-source desktop AI assistant supporting models from OpenAI (GPT-6, GPT-5, GPT-4, and others), Google Gemini, Anthropic Claude, xAI Grok, DeepSeek, Perplexity / Sonar, HuggingFace, OpenAI-compatible APIs, and local Ollama models such as DeepSeek, Qwen, gpt-oss, Gemma, Mistral, Llama, and others. PyGPT combines regular chat with agent workflows, RAG, Agent Skills, plugins, MCP, Python and system tools, vision, image and video generation, Computer use, web access, file handling, voice features, automation, and extensible tools. The application can work with local files and attachments, indexed knowledge, webpages, external data sources, images, audio/video, and conversation history. Models can execute Python and system commands, manage files, call external APIs, use web search, interact with connected services, and perform multi-step tasks using agents and tools. PyGPT also includes image analysis and camera support, image and video generation, speech recognition, speech synthesis, realtime voice conversations, conversation memory, presets, projects, profiles, and built-in utilities for everyday AI-assisted workflows. Features - Desktop AI assistant for Windows, Linux, and macOS, written in Python. - Supports OpenAI GPT-6, GPT-5, GPT-4, Google Gemini, Anthropic Claude, xAI Grok, DeepSeek, Perplexity / Sonar, HuggingFace, OpenAI-compatible APIs, and local Ollama models. - Chat, Agents, Realtime + audio, Research, Completion, Image and Video generation, Computer use, Experts, and legacy Agent / Autonomous modes. - Multi-agent workflows with primary agents, orchestrators, swarms, and dynamically managed worker agents. - Portable SKILL.md-based Agent Skills with catalog browsing and GitHub/local import. - MCP (Model Context Protocol) support with a built-in Connectors manager. - Integrated LlamaIndex RAG for files, webpages, external sources, media, and conversation history. - Built-in vector stores, embeddings, file indexing, context indexing, and isolated project indexes. - Built-in Python/OS tools with Python, IPython, system command execution, a built-in sandbox, and Docker support. - Local and provider-side tools/function calls, custom commands, filesystem access, and external API integrations. - Computer use with supported OpenAI, Google, and Anthropic models. - Vision support for image attachments, screenshots, camera captures, and other visual input. - Image generation with models such as gpt-image, Imagen, Gemini, Nano Banana, Grok, and others. - Video generation with models such as Veo and Sora. - Web search and retrieval using DuckDuckGo, Google, and Microsoft Bing. - Extensible plugin system for files, Python, web search, Google services, GitHub, Slack, Telegram, X/Twitter, MCP, and more. - File and attachment handling with native upload, local processing, RAG, summaries, downloads, and project-aware workdirs. - Short- and long-term conversation memory with optional advanced context handling for long conversations. - Integrated calendar, day notes, conversation history, and @mentions for files, attachments, and previous chats. - Speech recognition and speech synthesis with multiple cloud and local providers. - Realtime voice conversations with supported providers. - Crontab / Task scheduler for automated prompts and tasks. - Reusable presets for models, prompts, RAG, tools, and workflow configuration. - Multiple profiles with separate settings, history, and files, plus profile import/export. - Projects with optional isolated data workdirs and RAG indexes. - Project-specific AGENTS.md instructions for agent workflows. - Accessibility features including customizable keyboard shortcuts, voice control, and spoken UI feedback. - Built-in Notepad, Painter, Indexer, media tools, text editor, web browser, Python/OS, and Agent Workflow monitor. - Customizable themes, layouts, translations, and profile-level CSS/QSS overrides. - Real-time code syntax highlighting and token usage estimates. - Fully configurable and extensible with custom models, providers, plugins, vector stores, data loaders, and agents. - Uses your own provider API credentials; local models can run without external API keys. - Free and open source, with the full Python source code available on GitHub. Official website: https://pygpt.net Documentation: https://pygpt.readthedocs.io GitHub: https://github.com/szczyglis-dev/py-gpt
Productivity · Windows · Free
Rating: 4.2 out of 5, based on 10 user ratings.
