camelAI Documentation

Start Here

Use Hermes Agent

Point Hermes Agent at Camel Stream and run DeepSeek V4 Flash

Hermes Agent can use any OpenAI-compatible /v1/chat/completions endpoint as a custom provider.

Providercustom:camel-stream
Modeldeepseek-v4-flash
Base URLhttps://stream.camelai.com/v1
KeyCAMEL_API_KEY
Context window256k input tokens

Hermes is a third-party agent. Camel Stream provides the model. Review the Hermes security policy before connecting a key.

1. Install Hermes

Terminal
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
source ~/.zshrc

See the Hermes installation guide if you use bash or install from source.

2. Create a Stream key

Generate an API key in the Stream console. It is shown once. Put it in Hermes' env file, not in config.yaml.

~/.hermes/.env
CAMEL_API_KEY=qaml_live_...

3. Point Hermes at Stream

The fastest path is the built-in wizard, the same one OpenRouter documents:

Terminal
hermes model

Choose Custom endpoint, then enter:

FieldValue
URLhttps://stream.camelai.com/v1
API modeChat Completions
Keyyour CAMEL_API_KEY
Modeldeepseek-v4-flash
Context length262144

Or add a named custom provider to ~/.hermes/config.yaml:

~/.hermes/config.yaml
custom_providers:
  - name: camel-stream
    base_url: https://stream.camelai.com/v1
    key_env: CAMEL_API_KEY
    api_mode: chat_completions
    models:
      deepseek-v4-flash:
        context_length: 262144

model:
  provider: custom:camel-stream
  default: deepseek-v4-flash
  context_length: 262144

4. Start and verify

Terminal
hermes chat --provider custom:camel-stream --model deepseek-v4-flash

In a session you can switch with /model custom:camel-stream:deepseek-v4-flash.

Terminal
hermes doctor

hermes doctor should see the custom provider. If auth fails, confirm CAMEL_API_KEY is in ~/.hermes/.env.

Camel Stream queues requests when every subscribed stream is busy. Hermes should keep the HTTP connection open. See Queues & errors.

What's next?