Hermes Agent + Gonka AI — Autonomous Agent for Pennies

Hermes Agent is an open-source self-learning AI agent from Nous Research (MIT license). It's more than just a chat: a full-featured terminal CLI with memory, skills, a task planner, and a gateway to Telegram, Discord, Slack, and WhatsApp. The agent creates skills from experience, searches past dialogues, and builds a user model between sessions. It runs on anything from a $5 VPS to a GPU cluster.

The problem with Hermes is the same as with any agentic tool: token consumption. The agent reads files, runs tool-calling cycles, compresses context, maintains memory — active work easily consumes tens of millions of tokens. On Anthropic or OpenAI models ($3-15 per 1M), this turns into tens or hundreds of dollars per day of autonomous work.

Hermes supports any provider by default: Nous Portal, OpenRouter, OpenAI, Anthropic — or your own endpoint. This is the entry point for JoinGonka Gateway: our OpenAI-compatible gateway serves inference from the decentralized Gonka network at a price from $0.003 per 1M tokens — hundreds and thousands of times cheaper. Hermes becomes a truly everyday tool, rather than an expensive demonstration.

Step 1: Install Hermes and Get Your Key

Install Hermes (Linux, macOS, WSL2). The official installer will automatically pull Python, Node.js, ripgrep, and ffmpeg:

# Linux / macOS / WSL2
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

# Windows (PowerShell)
iex (irm https://hermes-agent.nousresearch.com/install.ps1)

After installation, restart your shell and check the launch:

source ~/.bashrc   # or ~/.zshrc
hermes             # interactive CLI

JoinGonka API key: If you don't have one yet — register at gate.joingonka.ai/register, get 10M free tokens, and create a key with the jg- prefix in the Dashboard. One key and one balance work for all models simultaneously.

Step 2: Connect Gonka as a custom provider

Hermes works with any OpenAI-compatible endpoint: if the server responds to /v1/chat/completions, Hermes can be pointed to it. The JoinGonka Gateway is exactly that. There are two ways to set it up.

Method 1: Setup wizard (recommended). Run in your terminal outside an active session:

hermes model

In the list of providers, select "Custom endpoint (self-hosted / VLLM / etc.)" and enter three values:

API base URL: https://gate.joingonka.ai/v1
API key: jg-your-key
Model name: MiniMaxAI/MiniMax-M2.7

Method 2: Edit config. Hermes stores model settings in ~/.hermes/config.yaml — this is the single source of truth. Add this section:

# ~/.hermes/config.yaml
model:
  provider: custom
  default: MiniMaxAI/MiniMax-M2.7
  base_url: https://gate.joingonka.ai/v1
  api_key: jg-your-key

Verification: run hermes and type "Create a hello.py file with a hello world function". The agent should create the file and show the result. The current configuration state can be seen via hermes config show | grep '^model\.' and hermes status.

Switching on the fly: within a session, use the command /model custom:MiniMaxAI/MiniMax-M2.7. Using /model custom without a name will automatically pull the model from the endpoint if there is only one available.

Comparison of Autonomous Session Costs

Hermes is an agentic tool with memory and skills. It doesn't just respond with a single message: it reads files, writes code, executes commands, compresses context, and performs long-running background tasks via a scheduler. Every action is an API call, and десятки millions of tokens accumulate during an autonomous workday. Let's compare the costs of typical sessions:

Task	Tokens	Anthropic Claude	JoinGonka Gonka
One-time task with tool-calling	~5M	$15 — $75	$0.024
Background agent (several hours)	~20M	$60 — $300	$0.096
Autonomous feature development	~50M	$150 — $750	$0.24
24h operation via gateway (Telegram + cron)	~150M	$450 — $2,250	$0.72

With JoinGonka Gateway, Hermes can be kept running 24/7: nightly reports, weekly audits, background tasks via a cron scheduler — without worrying about the bill. At Anthropic prices, each run would have to be calculated manually. The 10M free tokens included with registration are enough for dozens of full sessions.

Model selection and tool calling

Through the Gateway, two Gonka models are immediately available to the user — both support native tool calling (OpenAI function calling), so Hermes' skills and tools work reliably without parsing text responses:

Model name (for config)	Context	Max Response	When to choose
`moonshotai/Kimi-K2.6`	200K	8192	Default — strong reasoning, coding, and agentic scenarios
`MiniMaxAI/MiniMax-M2.7`	200K	8192	Long context, long tool-calling chains

About token limits in Hermes. In config.yaml, the context_length field is the total context window (input + output), while max_tokens is the ceiling for the response length only. It is best not to set either: Hermes will correctly determine the values from the provider itself. If you set max_tokens manually, keep it within the model's range — for both models, the maximum via the Gateway is 8192. You can change the model at any time with the hermes model command or directly in a session via /model.

Similar terminal tools in our knowledge base: Claude Code, Cline.

Hermes Agent + Gonka = autonomous AI-agent from Nous Research for pennies. A day of background work costs $0.15 instead of $450-2,250 with Anthropic. Setup — custom provider with our gateway's base_url, native tool calling, three models to choose from. 10M free tokens are enough for dozens of sessions.

← LibreChat + Gonka AI — open-source ChatGPT Kilo Code + Gonka AI — AI-Agent in VS Code →

Want to learn more?

Explore other sections or start earning GNK right now.

Get 10M free tokens →