GPT-4/GPT-3.5 Desktop AI Assistant

Open source personal AI Assistant for Linux, Windows and Mac, featuring chat, vision, completion, agents, image generation, command execution, voice control and more. It operates on the system desktop, utilizing OpenAI API key.

64-bit, release: 2.3.2 (2024-08-29), Changelog, GitHub, PyPi, Snap Store, Discord
PyPi
pip install pygpt-net
Snap
sudo snap install pygpt
PyGPT is a third-party software, not associated with OpenAI.
GitHub GitHub Repo stars GitHub Repo stars
MIT License.
❤️ Donate

Multiple features

Supports GPT-4, GPT-4V, GPT-3.5, and DALL-E 3, as well as all LLMs provided by Langchain/Llama-index, such as Llama 3, Mistral, Google Gemini, and Anthropic Claude. It features built-in internet search, speech synthesis and recognition, presets for prompts, conversation history, plugin support, and more.

9 modes of operation

The assistant offers multiple modes of operation: chat, completion, real-time vision analysis, image generation (via DALL-E 3), assistants (via the OpenAI Assistants API), experts, autonomous agents, and integration with LLMs provided by Langchain and Llama-index.

Full integration

The assistant can execute system commands, custom user commands, generate and execute Python code, and connect with any service, including access to the web. It allows the use of both local and external tools.

Open Source

The application is free to use. The only requirement is your own OpenAI API key (for GPT models). The source code can be found on GitHub. Compiled binary versions are available for both Windows and Linux.

Working modes

Features

  • Desktop AI Assistant for Linux, Windows and Mac, written in Python.
  • Works similarly to ChatGPT, but locally (on a desktop computer).
  • 9 modes of operation: Chat, Vision, Completion, Assistant, Image generation, Langchain, Chat with files, Experts and Agent (autonomous).
  • Supports multiple models: GPT-4, GPT-3.5, and any model accessible through Langchain and Llama-index such as Llama 3, Mistral, Google Gemini, Anthropic Claude, etc.
  • Included support features for individuals with disabilities: customizable keyboard shortcuts, voice control, and translation of on-screen actions into audio via speech synthesis.
  • Handles and stores the full context of conversations (short and long-term memory).
  • Real-time video camera capture in Vision mode.
  • Internet access via Google and Microsoft Bing.
  • Speech synthesis via Microsoft Azure, Google, Eleven Labs and OpenAI Text-To-Speech services.
  • Speech recognition via OpenAI Whisper, Google, Google Cloud and Microsoft Bing.
  • Image analysis via GPT-4 Vision.
  • Crontab / Task scheduler included.
  • Integrated Langchain support (you can connect to any LLM, e.g., on HuggingFace).
  • Integrated Llama-index support: chat with txt, pdf, csv, html, md, docx, json, epub, xlsx, xml, webpages, Google, GitHub, video/audio, images and other data types, or use conversation history as additional context provided to the model.
  • Integrated calendar, day notes and search in contexts by selected date.
  • Commands execution (via plugins: access to the local filesystem, Python code interpreter, system commands execution).
  • Custom commands creation and execution.
  • Manages files and attachments with options to upload, download, and organize.
  • Context history with the capability to revert to previous contexts (long-term memory).
  • Allows you to easily manage prompts with handy editable presets.
  • Provides an intuitive operation and interface.
  • Includes a notepad.
  • Includes simple painter / drawing tool.
  • Includes optional Autonomous Mode (Agents).
  • Supports multiple languages.
  • Requires no previous knowledge of using AI models.
  • Simplifies image generation using DALL-E 3 and DALL-E 2.
  • Possesses the potential to support future OpenAI models.
  • Fully configurable.
  • Themes support.
  • Real-time code syntax highlighting.
  • Plugins support.
  • Built-in token usage calculation.
  • It's open source; source code is available on GitHub.
  • Utilizes the user's own API key.
  • ...and many more.

Image generation Code highlighting Drawing tool Access to the filesystem

Download for free
or check it out on GitHub.

Download View source code on GitHub

Download v.2.3.2

build 2024-08-29, 64-bit

SHA-1 checksum:
pygpt-2.3.2.msi: 22bfac05be22d745ff96af87c6fcde6db6fbfc84
pygpt-2.3.2.tar.gz: 881a842507a014253af04d438ac6c810090c4d7d

install with PyPi:

pip install pygpt-net

install with Snap:

sudo snap install pygpt

Get it from the Snap Store
This website uses cookies to store session information and gather data for analytics. By using our site, you agree to our use of cookies.