# py-gpt

> Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, spe

- **URL**: https://www.freshcrate.ai/projects/py-gpt
- **Author**: szczyglis-dev
- **Category**: MCP Servers
- **Latest version**: `v2.7.12` (2026-02-06)
- **License**: NOASSERTION
- **Source**: https://github.com/szczyglis-dev/py-gpt
- **Homepage**: https://pygpt.net
- **Language**: Python
- **GitHub**: 1,738 stars, 320 forks
- **Registry**: github
- **Tags**: `ai`, `ai-assistant`, `artificial-intelligence`, `autonomous-agent`, `chatbot`, `claude`, `deepseek`, `desktop-app`, `python`

## Description

Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, speech synthesis and recognition, web search, memory, presets, assistants,and more. Linux, Windows, Mac

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v2.7.12` | 2026-02-06 | Low | - xAI SDK upgraded to v1.6.1. - Added video generation support in xAI provider. - Added new models: grok-imagine-image and grok-imagine-video. - UI improvements and smoother navigation between tabs and columns.   - Optimized adding attachments. Added options to attach an attachment only once (if the API stores messages on its side), and an option to force attaching an attachment only once.   - Updated libraries. |
| `v2.7.11` | 2026-02-05 | Low | - Improved handling focus between columns. - Fixed models debugger update. |
| `v2.7.10` | 2026-02-03 | Low | - Fixed an issue where an avatar could be overwritten when creating a new preset.   - Fixed an issue where a new context was not created when opening a new tab in the second column.   - Added prompt history navigation to the input field (Ctrl + Up/Down arrow keys).   - Added initial image centering when loading the Image Viewer.   - Added a Mark/Unmark feature to the Notepad widget.   - Added 18 new languages: Arabic (ar), Bulgarian (bg), Czech (cs), Danish (da), Finnish (fi), Hebrew (he), |
| `v2.7.9` | 2026-01-08 | Low | - Improved realtime audio mode. - Added xAI provider and Grok support in realtime audio mode. |
| `v2.7.8` | 2026-01-06 | Low | - Added the xAI Collections remote tool and integrated collections management into the Remote Vector Stores tool. - Unified the Remote Vector Stores tool into a single tool for all providers. - Added xAI Grok audio input and output provider (realtime audio support for Grok coming soon!). - Enhanced the Image Viewer tool with a toolbox featuring Prev/Next and more options. |
| `v2.7.7` | 2026-01-05 | Low | - Added support for Responses API in xAI. - Added xAI remote tools: Remote MCP, Code Execution. - Added Anthropic remote tools: Remote MCP, Web Fetch, Code Execution. |
| `v2.7.6` | 2026-01-03 | Low | - Fixed compatibility with xAI SDK and resolved empty responses from Grok models. - Fixed missing libraries in the Snap package. - Added zoom and grab functionality in the Image Viewer. - Added a zoom menu to textarea and web widgets. - Added the ability to close tabs with a middle mouse button click. |
| `v2.7.5` | 2026-01-03 | Low | - Added Sandbox/Playwright option to Computer Use mode. - Added support for Google models in Computer Use mode and introduced a new model: gemini-2.5-computer-use-preview-10-2025. - Added support for Google models in Research mode and introduced a new model: deep-research-pro-preview-12-2025. - Added the Google Vector Stores tool. |
| `v2.7.4` | 2025-12-31 | Low | - Added a splash screen. - Added Preview and Download links to the Image and Video outputs. - Added Negative prompt input to Image and Video mode. - Improved focus handling. - UI improvements. |
| `v2.7.3` | 2025-12-30 | Low | - Added the `Remix/Extend` option in Image and Video generation mode. This allows the use of a previously generated image or video as a reference. It can be used for adding or changing elements in a previously generated image or video instead of creating a new one from scratch. See the docs: `Modes -> Image and Video generation -> Remix, Edit, or Extend`. |

## Citation

- HTML: https://www.freshcrate.ai/projects/py-gpt
- Markdown: https://www.freshcrate.ai/projects/py-gpt.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/py-gpt/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._