OpenClaw is a self-hosted gateway that connects chat interfaces and communication channels to AI-powered agents.
Official documentation: https://docs.openclaw.ai
1.1 Setup Options
Method 1: Configuration File or Guided Setup (Recommended)
You can initialize OpenClaw using the interactive onboarding flow:
openclaw onboardAlternatively, you may directly edit the configuration file located at:
~/.openclaw/openclaw.jsonIf your setup uses a different path, retrieve it with:
openclaw config fileConfiguration Steps
- Define a custom provider inside
models.providers - Use OpenAI-compatible transport:
api:openai-completionsbaseUrl:https://api.rygen.io/v1
- Assign a default model using the provider/model format
- Provide your API key directly or via environment variables / secret references
Example Configuration
{
"models": {
"providers": {
"rygen": {
"baseUrl": "https://api.rygen.io/v1",
"api": "openai-completions",
"apiKey": "your-rygen-api-key",
"models": [
{
"id": "minimax/minimax-m2.5",
"name": "Rygen Minimax M2.5",
"reasoning": false,
"input": ["text"],
"contextWindow": 128000,
"maxTokens": 8192
}
]
}
}
},
"agents": {
"defaults": {
"model": { "primary": "rygen/minimax/minimax-m2.5" }
}
}
}Method 2: Non-Interactive Setup
For automated environments, you can configure OpenClaw without prompts:
export CUSTOM_API_KEY="your-rygen-api-key"
openclaw onboard --non-interactive \
--auth-choice custom-api-key \
--custom-base-url "https://api.rygen.io/v1" \
--custom-model-id "minimax/minimax-m2.5" \
--custom-api-key "$CUSTOM_API_KEY" \
--secret-input-mode plaintext \
--custom-compatibility openai
