# Proxmox AI agent with Gemini and Gmail: n8n workflow template

> Started by an incoming Telegram message, and works across Gmail and Telegram. It hands the judgement calls to Gemini.

Source: https://millionrounds.com/workflow/proxmox-ai-agent-with-gemini-and-gmail (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Chat assistants](https://millionrounds.com/workflows?category=Chat+assistants#library)

# Proxmox AI agent with Gemini and Gmail

Started by an incoming Telegram message, and works across Gmail and Telegram. It hands the judgement calls to Gemini. 27 steps, 3 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: Gemini

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fproxmox-ai-agent-with-gemini-and-gmail)

**27 steps** Large: read it before trusting it with anything live

**3** Branches: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 4 Model 10 Logic 8 Service 5

The steps in the order they run, from what starts it.

- 1 **Proxmox API Documentation** Tool Http Request *Model*
- 2 **Google Gemini Chat Model1** Lm Chat Google Gemini *Model*
- 3 **Structured Output Parser** Output Parser Structured *Model*
- 4 **Proxmox** Tool Http Request *Model*
- 5 **Google Gemini Chat Model2** Lm Chat Google Gemini *Model*
- 6 **When chat message received** Chat trigger *Starts it*
- 7 **Telegram Trigger** Telegram trigger *Starts it*
- 8 **Gmail Trigger** Gmail trigger *Starts it*
- 9 **Webhook** Webhook *Starts it*
- 10 **Proxmox API Wiki** Tool Http Request *Model*
- 11 **Google Gemini Chat Model** Lm Chat Google Gemini *Model*
- 12 **AI Agent** Agent *Model*
- 13 **Auto-fixing Output Parser** Output Parser Autofixing *Model*
- 14 **AI Agent1** Agent *Model*
- 15 **Switch** Switch *Logic*
- 16 **HTTP Request** Http Request *Service*
- 17 **If** If *Logic*
- 18 **If1** If *Logic*
- 19 **Structure Response** Code *Logic*
- 20 **HTTP Request1** Http Request *Service*
- 21 **HTTP Request2** Http Request *Service*
- 22 **HTTP Request3** Http Request *Service*
- 23 **HTTP Request4** Http Request *Service*
- 24 **Merge** Merge *Logic*
- 25 **Merge1** Merge *Logic*
- 26 **Structgure Response from Proxmox** Code *Logic*
- 27 **Format Response and Hide Sensitive Data** Code *Logic*

## How it's built

- **Starts on:** An incoming Telegram message
- **Steps:** 27, with 3 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Gmail, Telegram
- **Model:** Gemini

## Questions

What does it need to run?

An n8n account, plus your own Gmail and Telegram accounts, and a key for Gemini. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an incoming Telegram message.

Does it use AI?

Yes. It calls Gemini. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 27 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 27 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fproxmox-ai-agent-with-gemini-and-gmail)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Gmail](https://millionrounds.com/workflows?service=Gmail#library)[Telegram](https://millionrounds.com/workflows?service=Telegram#library)

## Workflows like it

Also chat assistants, with the same services where possible, closest in size first.

- [**ASMR YouTube shorts automation with Claude and Gmail** 27 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/asmr-youtube-shorts-automation-with-claude-and-gmail)
- [**Analyze event feedback with Gemini and Discord** 27 steps · calls a model · Discord, Gmail](https://millionrounds.com/workflow/analyze-event-feedback-with-gemini-and-discord)
- [**Create & upload AI-generated ASMR YouTube Shorts with Seedance** 27 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/create-and-upload-ai-generated-asmr-youtube-shorts-with-seed)
- [**Create ASMR YouTube Shorts with OpenAI and Wavespeed Seedance** 27 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/create-asmr-youtube-shorts-with-openai-and-wavespeed-seedanc)
- [**Nano Banana/Gemini 2.5 Telegram bot with OpenAI** 27 steps · calls a model · Telegram](https://millionrounds.com/workflow/nano-banana-gemini-2-5-telegram-bot-with-openai)
- [**Refresh Webflow directory listings from Google Maps** 27 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/refresh-webflow-directory-listings-from-google-maps)