Hermes Agent
Use TensorX models with Hermes Agent — the self-improving AI agent by Nous Research.
Overview
Hermes Agent is an open-source AI agent built by Nous Research that learns from experience, creates skills autonomously, and works across CLI, Telegram, Discord, Slack, and WhatsApp. It supports custom OpenAI-compatible endpoints via environment variables or config.
Prerequisites
Linux, macOS, or WSL2 (native Windows not supported)
Git
A TensorX API key (sign up here)
Installation
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
source ~/.bashrcConfiguration
Option 1: Setup Wizard
When prompted for provider, choose Custom/OpenAI-compatible and enter:
Base URL
https://api.tensorx.ai/v1
API Key
Your TensorX API key
Model
z-ai/glm-5.3
Option 2: Environment Variables
To make permanent, add to ~/.bashrc or ~/.zshrc.
Option 3: Config File
Edit ~/.hermes/config.yaml:
Usage
Model selection
Call GET /v1/models with your TensorX API key and use one of the returned IDs. If the integration depends on a capability or token limit, query GET /v1/model/info before selecting the model. See Models for examples.
Messaging Gateway
Connect your agent to messaging platforms:
Hermes Agent supports Telegram, Discord, Slack, and WhatsApp — all from a single gateway process with cross-platform conversation continuity.
Troubleshooting
Agent Not Responding
Verify your environment variables:
Run diagnostics:
Model Errors
Switch models with:
See Also
Last updated
Was this helpful?

