PyGPT: review, pricing, security and alternatives

What PyGPT does

PyGPT belongs to the chat interfaces family: multi-model chat interfaces, often self-hostable, with built-in tools, agents and MCP servers. On our grid it ranks #12 of the 17 projects of this family listed in the directory.

You use it from: desktop app. Usable models: GPT (OpenAI), Gemini (Google), Claude (Anthropic), Grok (xAI), local models (Ollama, llama.cpp, vLLM…), and DeepSeek. It can run on your own machine or server.

Who is PyGPT for?

It targets people who want a single chat interface for several models, often self-hosted, with tools and agents plugged in. Typical tasks people give it:

• chat with several models from one window
• share an internal assistant with a team
• connect documents and tools to the chat

It is a good candidate if your data must stay on your machines and you want the option of a local model, with no API fees.

Access and human control

According to its documentation, PyGPT can:

• drive a web browser
• control the screen, keyboard and mouse

We could not establish whether it asks for human approval before sensitive actions: test it first on an unimportant account or folder.

PyGPT pricing

The code is public but the repository declares no licence: reuse is not formally allowed. The real cost comes from model calls: each loop step sends the whole context back to the model, and a task of several dozen steps can cost far more than a single question. The LLM price calculator estimates it for the chosen model.

Getting started with PyGPT

1. Install it: the project ships as a Python package (install with pip or uv). The exact command is in the repository README.
2. Pick the model: an API key from a provider, or a local model if your machine has enough graphics memory (the VRAM calculator tells you).
3. Give it a first playground with nothing at stake: a test folder, a secondary account or a throwaway project. Only open your real accounts once you have seen how it behaves.
4. Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.

Security: risk level

The interface stores your API keys and conversation history: protect its access and backups.

Points found for PyGPT:

• Sensitive access: it can control the screen, keyboard and mouse, with no established default human approval.
• Outside content: it reads web pages or API responses, which may contain booby-trapped instructions (prompt injection).
• No licence: legally shaky for company use.

Three habits: least privilege (minimal rights, dedicated keys), human approval for irreversible actions, a sandbox for code execution. The AI agent security check reviews your setup in a few minutes.

Project activity and releases

Created on April 9, 2023, the szczyglis-dev/py-gpt repository has 2,002 stars, 353 forks and 48 open issues, with 5,438 commits in total. It received changes this month.

Over the last 52 weeks: 1,134 commits, an average of 21.8 per week.

576 releases in total; 30 in the last twelve months. Latest release: v2.9.1, on October 6, 2026.

PyGPT vs other chat interfaces

GitHub stars of the best-rated open-source projects in the chat interfaces family. Stars measure attention, not quality: a heavily promoted project collects them fast, a specialised tool will have few.

PyGPT and other chat interfaces at a glance

The 7 best-ranked agents in the same family, 7 of them open source. The score out of 100 only applies to open-source projects; for proprietary services we show the published entry price. A dash marks information the documentation does not state.

How we rated it

Score: 61/100, computed only from public, verifiable data, with no subjective testing or partnership:

• Adoption 16/40: 2,002 stars on a log scale (40 points from about 200,000).
• Activity 30/30: last commit less than a month ago, 30 releases in six months, 1,134 commits in a year.
• Framework 15/30: licence, default human approval, self-hosting, model choice and documentation site.

The score does not say whether the agent will succeed at your tasks: it measures how solid the project is. The full grid is on the method page.