Tools

Tools: Ultimate Guide: GCP in Action: Building a Persistent AI Assistant with GCE, Hermes Agent, and Telegram

2026-05-02 0 views admin
Tools: Ultimate Guide: GCP in Action: Building a Persistent AI Assistant with GCE, Hermes Agent, and Telegram

Background

Environment Parameter Preparation

Step 1: Create a GCE Instance

Step 2: Install Hermes Agent

Step 3: Configure Gemini 2.5 Flash (SOP Practice)

Step 4: Connect to Telegram and Background Persistence

Blood and Tears in the Migration Process: Why Isn't My Agent Responding?

Pitfall 1: The 404 Ghost of Gemini 3.0

Pitfall 2: Prefix Confusion of Model Identifiers

Pitfall 3: Conflict between Systemd and "Processes Already Running"

Summary After solving the LINE Bot's Vertex AI migration, I started thinking: Could there be an AI assistant that is "more proactive" and "has long-term memory"? At this time, I set my sights on NousResearch's open-source Hermes Agent. Unlike a typical Chatbot, Hermes is designed as an "operating system that breathes". It can execute Shell commands, write Python scripts, manage long-term memory, and even stay in touch with you via different Gateways (Telegram, Discord) at any time. To make it available 24/7, I chose to deploy it on Google Compute Engine (GCE). This article will document the deployment process from scratch, as well as the pitfalls I encountered when configuring the latest Gemini 2.5 Flash model. Before you start, please make sure you have these necessary parameters: Hermes Agent needs some computing power to handle tool use. It is recommended to use the e2-medium specification. After SSHing into the VM, use the official one-click installation script directly. This is the most likely place to step on a landmine in the entire exercise. Hermes may default to pointing to non-existent or outdated model identifiers. Create a configuration file: In ~/.hermes/config.yaml, we must precisely specify Gemini 2.5 Flash, and do not include the google/ prefix. Set the API Key: Write the key and permission settings in ~/.hermes/.env: To prevent the Agent from disappearing after the SSH connection is lost, we use Systemd to manage it. Even with the correct configuration, I still encountered the dilemma of "the Agent reads messages but doesn't reply". After checking the logs (journalctl -u hermes), I found several deep pitfalls: I tried to pursue the latest version when configuring, and used gemini-3-flash-preview. As a result, the logs spewed out a bunch of 404 Model Not Found. Reason: The internal auxiliary_client.py of Hermes hardcodes many gemini-3-flash-preview as the default value. When these auxiliary functions (such as generating titles) report errors, it will affect the reply logic of the entire Gateway. Solution: Manually define all auxiliary models as gemini-2.5-flash in config.yaml, or directly patch the source code with sed. In different SDKs, some people use google/gemini-2.5-flash, and some people use gemini-2.5-flash. Experience: In Hermes' Gemini Provider, using the short name gemini-2.5-flash directly is the safest. Adding google/ will instead cause API routing errors. When you manually run hermes gateway and then start the service, the system will report Gateway already running (PID xxxx). Solution: Before ExecStart in Systemd, you can add an ExecStartPre=/usr/bin/pkill -9 -f hermes || true to ensure a clean environment every time you start. Now, my dedicated Hermes Agent is running stably on GCE and is available via Telegram at any time. It can not only help me find information, but also run some simple computing scripts for me directly on the cloud VM. This deployment taught me: In the face of rapidly updating models, the official documentation (or MCP tool query) is the only truth. Don't blindly pursue the latest version number; ensuring that the identifier matches the current API environment is the key to stable operation. If you also want a 24-hour AI digital double, get a machine set up according to this SOP! Templates let you quickly answer FAQs or store snippets for re-use. Hide child comments as well For further actions, you may consider blocking this person and/or reporting abuse

Code Block

Copy

gcloud compute instances create hermes-agent-vm \ --project=YOUR_PROJECT_ID \ --zone=us-central1-a \ --machine-type=e2-medium \ --image-family=ubuntu-2204-lts \ --image-project=ubuntu-os-cloud \ --boot-disk-size=30GB \ --metadata=startup-script='#!/bin/bash apt-get update apt-get install -y git curl python3-pip python3-venv nodejs npm ' gcloud compute instances create hermes-agent-vm \ --project=YOUR_PROJECT_ID \ --zone=us-central1-a \ --machine-type=e2-medium \ --image-family=ubuntu-2204-lts \ --image-project=ubuntu-os-cloud \ --boot-disk-size=30GB \ --metadata=startup-script='#!/bin/bash apt-get update apt-get install -y git curl python3-pip python3-venv nodejs npm ' gcloud compute instances create hermes-agent-vm \ --project=YOUR_PROJECT_ID \ --zone=us-central1-a \ --machine-type=e2-medium \ --image-family=ubuntu-2204-lts \ --image-project=ubuntu-os-cloud \ --boot-disk-size=30GB \ --metadata=startup-script='#!/bin/bash apt-get update apt-get install -y git curl python3-pip python3-venv nodejs npm ' gcloud compute ssh hermes-agent-vm --zone=us-central1-a gcloud compute ssh hermes-agent-vm --zone=us-central1-a gcloud compute ssh hermes-agent-vm --zone=us-central1-a curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash source ~/.bashrc curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash source ~/.bashrc curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash source ~/.bashrc [Unit] Description=Hermes Agent Gateway After=network.target [Service] Type=simple User=root Environment=HOME=/root Environment=PYTHONUNBUFFERED=1 ExecStart=/usr/local/lib/hermes-agent/venv/bin/hermes gateway run Restart=always RestartSec=10 [Install] WantedBy=multi-user.target [Unit] Description=Hermes Agent Gateway After=network.target [Service] Type=simple User=root Environment=HOME=/root Environment=PYTHONUNBUFFERED=1 ExecStart=/usr/local/lib/hermes-agent/venv/bin/hermes gateway run Restart=always RestartSec=10 [Install] WantedBy=multi-user.target [Unit] Description=Hermes Agent Gateway After=network.target [Service] Type=simple User=root Environment=HOME=/root Environment=PYTHONUNBUFFERED=1 ExecStart=/usr/local/lib/hermes-agent/venv/bin/hermes gateway run Restart=always RestartSec=10 [Install] WantedBy=multi-user.target sudo systemctl daemon-reload sudo systemctl enable hermes sudo systemctl restart hermes sudo systemctl daemon-reload sudo systemctl enable hermes sudo systemctl restart hermes sudo systemctl daemon-reload sudo systemctl enable hermes sudo systemctl restart hermes - PROJECT_ID: YOUR_PROJECT_ID - LOCATION: global - GOOGLE_API_KEY: YOUR_GOOGLE_API_KEY (Obtained from Google AI Studio) - Enter the VM: - Execute the installation: - Create a configuration file: In ~/.hermes/config.yaml, we must precisely specify Gemini 2.5 Flash, and do not include the google/ prefix. - Set the API Key: Write the key and permission settings in ~/.hermes/.env: - Create a Systemd service (/etc/systemd/system/hermes.service): - Start the service:

🏷️ Tags

toolsutilitiessecurity toolsultimateguideactionbuildingpersistentassistanthermes

More from Tools

Tools: How to Deploy Llama 3.2 1B with Ollama on a $4/Month DigitalOcean Droplet: Sub-$50/Year Edge AI Inference (2026)

Tools: How to Deploy Llama 3.2 1B with Ollama on a $4/Month DigitalOcean Droplet: Sub-$50/Year Edge AI Inference (2026)

2026-05-02 0
Tools: GCP Hands-on: Deploying OpenAB - Building a Gemini ACP Bridge for Telegram on GCE (2026)

Tools: GCP Hands-on: Deploying OpenAB - Building a Gemini ACP Bridge for Telegram on GCE (2026)

2026-05-02 0
Tools: I built a production-ready Wazuh SIEM on Docker (with custom rules for VMware, AWS and GCP) How

Tools: I built a production-ready Wazuh SIEM on Docker (with custom rules for VMware, AWS and GCP) How

2026-05-02 0
Tools: How to Deploy a Node.js App on Heroku in 2026

Tools: How to Deploy a Node.js App on Heroku in 2026

2026-05-02 0

Trending

1

CVE-2025-61481: Critical Remote Code Execution Vulnerability in MikroTik RouterOS & SwitchOS

2025-10-27 • 189 views
2

CVE-2025-43939: Dell Unity OS Command Injection (High)

2025-10-30 • 148 views
3

Google disputes false claims of massive Gmail data breach

2025-10-30 • 130 views
4

Microsoft: DNS outage impacts Azure and Microsoft 365 services

2025-10-30 • 88 views
5

3.5B Accounts, 1 Critical Flaw: Meta Closes WhatsApp Data-Harvesting

2025-11-25 • 81 views