Use LithosAI with Hermes Agent

Before you begin

Install Hermes Agent CLI, create a key on the API Keys page, and choose a model on the Models page.

Set your API key

Add your key to ~/.hermes/.env:

Hermes API key configuration

~/.hermes/.env

LITHOSAI_API_KEY=your-key

Configure LithosAI

The configuration uses deepseek-ai/DeepSeek-V4.1-Flash as an example.Merge into ~/.hermes/config.yaml, keeping existing providers. Set context_length to match your model, with a minimum of 64,000 tokens.

Hermes configuration

~/.hermes/config.yaml

providers:
  lithosai:
    api: https://api.lithosai.cloud/v1
    key_env: LITHOSAI_API_KEY
    transport: chat_completions
    default_model: deepseek-ai/DeepSeek-V4.1-Flash
    discover_models: false
    context_length: 1048576
    models:
      deepseek-ai/DeepSeek-V4.1-Flash:
        context_length: 1048576
        supports_reasoning: true
model:
  default: deepseek-ai/DeepSeek-V4.1-Flash
  provider: custom:lithosai
agent:
  reasoning_effort: high

To add another model or tier, copy the entry under providers.lithosai.models. Use its ID from the model catalog as the new key, and set context_length to match the model. Reopen Hermes to load the changes.

Start a conversation

Run hermes to start a conversation.

Getting Started

Models

Inference APIs

Account

Use LithosAI with Hermes Agent

Before you begin

Model and reasoning effort

Resources

​Before you begin

​Model and reasoning effort

​Resources

Before you begin

Model and reasoning effort

Resources