Skip to main content

​
Configure Clawdbot to Use Vivgrid

By configuring Clawdbot to use Vivgrid as its model provider, you can access advanced large language models through a single, stable endpoint. Vivgrid acts as an LLM gateway that manages model selection, upgrades, and routing, so Clawdbot does not need to bind to a specific model or vendor.
Make sure you have your Vivgrid API key ready. You can find it in your Vivgrid Console.
After installing Clawdbot, you should execute clawdbot onboard at first, then, configure Vivgrid as a model provider and set the agent to use the managed model. Vivgrid will handle the underlying LLM selection for you.
~/.clawdbot/clawdbot.json
{
  "models": {
    "providers": {
      "vivgrid": {
        "baseUrl": "https://api.vivgrid.com/v1",
        "apiKey": "viv-clawdbot-xxxxxxxxxxxxxxxxxxxx",
        "api": "openai-completions",
        "models": [
          {
            "id": "managed",
            "name": "managed",
            "contextWindow": 128000
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "maxConcurrent": 4,
      "subagents": {
        "maxConcurrent": 8
      },
      "compaction": {
        "mode": "safeguard"
      },
      "workspace": "/home/cc/clawd",
      "model": {
        "primary": "vivgrid/managed"
      }
    }
  },
  // ... other configurations ...
}

​
Restart Clawdbot Service

clawdbot daemon restart
and check your logs 
clawdbot logs --follow

​
Best practice

Use vivgrid/managed as the primary model for Clawdbot agents. By setting the model to vivgrid/managed, Clawdbot connects to Vivgrid’s managed routing layer instead of a fixed LLM. This allows you to:
  • Upgrade or switch underlying LLMs at any time from the Vivgrid Console
  • Avoid changing clawdbot.json when models evolve
  • Eliminate service restarts for model upgrades
  • Keep your agent configuration stable and future-proof
This is the recommended setup for production environments.