tencent cloud

LLM Service TokenHub

DokumentasiLLM Service TokenHubAI Tools IntegrationHermes Agent

Hermes Agent

Unduh
Mode fokus
Ukuran font
Terakhir diperbarui: 2026-06-11 17:53:15
Hermes Agent is an autonomous AI agent framework open-sourced by Nous Research. You can deploy it on a local server and connect it to various large language models. It can remember across sessions, automatically create skills, and continuously self-evolve to complete complex automated tasks. This article demonstrates how to integrate a model, using DeepSeek V4 Pro as an example, for use with Hermes Agent.

Installing Hermes Agent

Install Hermes Agent according to your actual environment type. For details, see Hermes Agent Installation. If Hermes Agent is already installed, you can skip this step.

Obtaining an API Key

1. Go to the API Key Management page and click Create API Key. For operational details, see Create API Key.
Note:
When setting the Access Scope, if you select "Range", ensure that DeepSeek V4 Pro is selected.
2. After creation, be sure to copy and securely store the API Key. This information will be used in the subsequent process of configuring the tool.


Configuring Hermes Agent

Note:
Configuration steps may be adjusted depending on the Agent version. Please refer to the version you are using.
1. Open a terminal and run the following command:
hermes setup
2. If this is your first launch after installation, the terminal will display the following message: select Quick setup — provider, model & messaging (recommended).

Note:
If you have previously configured Hermes Agent, after you run `hermes setup`, the terminal output may appear as shown in the following figure. In this case, select Model & Provider to proceed to model configuration.

3. After you make your selection, the terminal will display the available model providers. Scroll to the bottom, select Custom endpoint, and press Enter to confirm.

4. Configure model information: Fill in the relevant configurations step by step according to the terminal prompts.
Terminal Prompt Message
Configuration Details
API base URL [e.g. https://api.example.com/v1]:
https://tokenhub-intl.tencentcloudmaas.com/v1
API key [optional]:
Enter the corresponding API Key.
API compatibility mode
Select Chat Completions.
Model name (e.g. gpt-4, llama-3-70b):
Enter deepseek-v4-pro
Context length in tokens [leave blank for auto-detect]:
Enter 256000
Display name
Enter deepseek-v4-pro
Terminal backend
Fill in based on the actual situation. Select Local if it is installed locally.
Gateway working directory
Configure based on actual requirements. The default value can be used.
Enable sudo support
Whether to allow sudo. Fill in based on your requirements. Selecting sudo requires entering a password.


Using Hermes Agent

After completing the configuration, execute the hermes command in the terminal to start Hermes and begin a conversation using DeepSeek V4 Pro.





Topik sebelumnya: OpenClawTopik selanjutnya: OpenCode

Bantuan dan Dukungan

Apakah halaman ini membantu?

masukan