PyGPT

What is PyGPT?

PyGPT is an open-source desktop AI assistant written in Python for Windows, Linux and macOS. Instead of tying you to one vendor, it connects to OpenAI GPT models, Google Gemini, Anthropic Claude, xAI Grok, DeepSeek, Perplexity, Hugging Face, any OpenAI-compatible API and local models run through Ollama. The app offers separate modes for conversation, agents, live audio, research, text completion, image and video generation, computer use and autonomous operation. Agents can run in primary, orchestrator or swarm workflows, and portable Agent Skills based on SKILL.md files can be imported from GitHub or disk. LlamaIndex powers retrieval over files, web pages and conversation history, while built-in tools run Python and system commands, search the web, and connect to MCP servers. A scheduler automates recurring prompts, and voice, vision, a Painter sketch tool, a notepad and a calendar are included. PyGPT is free; you use your own provider API keys, and local models need none.

Use cases

• Chat with several AI models in one app
• Run local Ollama models without API keys
• Search your files with built-in RAG
• Automate recurring prompts with a scheduler
• Build multi-agent workflows on the desktop
• Generate images and videos from prompts
• Talk to an assistant with voice input

Who it's for

• Power users
• Developers
• Privacy-minded users
• AI hobbyists

Why use PyGPT

• The app is free and open source, so the only costs are the model providers you choose to call.
• One interface covers many cloud and local models, which makes it easy to compare them or switch.
• Conversation data and configuration are stored locally unless a feature or provider needs to send data out.
• Agents, RAG, MCP and scheduling are built in, so you do not need separate tools for those jobs.

PyGPT features

• Support for OpenAI, Gemini, Claude, Grok, DeepSeek, Perplexity and Hugging Face models
• Local models through Ollama such as Llama, Mistral, Gemma and Qwen
• Agents with primary, orchestrator and swarm workflows
• Portable Agent Skills based on SKILL.md with GitHub or local import
• MCP support with a built-in connectors manager
• LlamaIndex RAG over files, web pages, media and conversation history
• Python, IPython and system command tools with a sandbox and Docker support
• Computer use with supported OpenAI, Google and Anthropic models
• Image generation and video generation with models such as Veo and Sora
• Speech recognition, speech synthesis and realtime voice
• Task scheduler, reusable presets and multiple profiles
• Plugin system for files, web search, GitHub, Slack, Telegram and more

PyGPT integrations

• OpenAI
• Google Gemini
• Anthropic Claude
• xAI Grok
• DeepSeek
• Perplexity
• Hugging Face
• Ollama
• LlamaIndex
• GitHub
• Slack
• Telegram
• DuckDuckGo
• Microsoft Bing

How to get started with PyGPT

1. Install PyGPT from PyPI with pip install pygpt-net, or use the Windows MSI, Linux AppImage or another release from GitHub.
2. Add API keys for the providers you want, or point the app to local Ollama models.
3. Pick a work mode such as Chat, Agents, Research or Realtime audio and choose a model.
4. Enable plugins, RAG indexes, MCP connectors or Agent Skills for the task.
5. Optionally schedule recurring prompts, save presets and keep separate profiles for different projects.

PyGPT limitations

• You supply your own API keys, and provider usage charges apply
• Agents, multimodal requests and multi-step tasks can trigger extra API requests and cost
• AI responses can be inaccurate and should be checked before you rely on them
• Local models need hardware able to run them

PyGPT pricing

PyGPT is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

PyGPT alternatives

The main PyGPT alternatives listed on Debuly are Open WebUI, LM Studio, Jan, Msty, AnythingLLM and BrainSoup. The table compares pricing and platforms; order is A–Z.

1. 

   AnythingLLM

   Open-source AI app for chatting with your documents and running agents, on desktop, in Docker or as a hosted team workspace.

   Chat assistantsAutomation and agentsDeveloper platforms
   Open sourceVisit AnythingLLM (official site)
2. 

   BrainSoup

   Native Windows app for building teams of custom AI agents that you direct in plain language, with local or cloud models and your own documents.

   Automation and agentsChat assistantsProductivity
   PaidVisit BrainSoup (official site)
3. 

   Jan

   Free, open-source desktop AI assistant that runs models offline on your computer or connects to cloud models with your own keys.

   Chat assistantsDeveloper platforms
   Open sourceVisit Jan (official site)
4. 

   LM Studio

   Desktop app for running open language models on your own computer, now with the Bionic agent, a local API and optional US-hosted cloud models.

   Chat assistantsDeveloper platformsCodingProductivity
   FreemiumVisit LM Studio (official site)
5. 

   Msty

   Privacy-first AI workspace for chatting with local and online models, with a model gateway, agents and knowledge stacks.

   Chat assistantsAutomation and agentsDeveloper platforms
   FreemiumVisit Msty (official site)
6. 

   Open WebUI

   Self-hosted AI chat platform for Ollama and OpenAI-compatible models with RAG, agents, tools, notes, channels and role-based access.

   Chat assistantsDeveloper platformsAutomation and agents
   Open sourceVisit Open WebUI (official site)

PyGPT FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from pygpt.net · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.