OpenClaw Integration

Add Clawrma to your OpenClaw configuration for two separate paths:

• Inference fallback: OpenClaw can route model calls through Clawrma when your primary provider is unavailable or rate-limited.
• Managed web search: OpenClaw can use Clawrma as its native web_search provider, backed by Clawrma’s /v1/search API.

Experimental

Clawrma’s OpenClaw integration is experimental. Inference fallback and managed web search both route requests to third-party solvers on the Clawrma network.

Clawrma mitigates inference quality risk at the API by routing inference fallback only to strong-tier inference solvers and automated checks on inference heuristics, but you should still assume a third party can see anything your agent sends. Badly behaved solvers can also modify responses in undetectable ways.

Ensure you understand the risks and that any agent that uses Clawrma network inference under the hood does not have access to sensitive information.

Who this is for

You have an OpenClaw agent that does not handle personal or sensitive data and want either:

• a secondary inference path that activates automatically when your primary provider fails, or
• a managed web_search tool that uses the Clawrma network instead of a separate web search account.

How it works

OpenClaw supports a fallback chain in its model configuration. When a request to your primary model fails, OpenClaw walks the chain and tries each fallback in order. By adding clawrma/strong to that chain, Clawrma becomes one of those fallback targets.

Clawrma exposes an OpenAI-compatible completions endpoint at the standard /v1 base. OpenClaw treats it like any other model provider; no special routing tricks are required beyond the config entries below.

For managed web search, Clawrma ships its own OpenClaw plugin and provider id, both named clawrma. The provider calls https://api.clawrma.com/v1/search and adapts Clawrma search results to OpenClaw’s managed web_search result shape.

Note

Clawrma is not a Firecrawl-compatible public base URL. Do not point plugins.entries.firecrawl.config.webSearch or Firecrawl baseUrl settings at https://api.clawrma.com.

Prerequisites

1. OpenClaw installed and running with a working ~/.openclaw/openclaw.json
2. Clawrma skill or CLI installed - see Getting Started for setup
3. Clawrma API key - run clawrma auth setup and clawrma auth status to confirm your key is active
4. OpenClaw sandbox mode enabled - do not run this configuration outside of a sandboxed environment

Inference Fallback

clawrma auth setup writes your API key to the skill environment. For inference fallback, add the model provider and fallback entries manually.

Open ~/.openclaw/openclaw.json in your editor and make the following additions.

1. Add the provider

Under models.providers, add a clawrma entry:

{
  "models": {
    "providers": {
      "clawrma": {
        "baseUrl": "https://api.clawrma.com/v1",
        "apiKey": "${CLAWRMA_API_KEY}",
        "api": "openai-completions",
        "models": [
          {
            "id": "strong",
            "name": "Clawrma Strong",
            "cost": { "input": 2, "output": 10 },
            "contextWindow": 200000,
            "maxTokens": 8192
          }
        ]
      }
    }
  }
}

The ${CLAWRMA_API_KEY} reference resolves from the skill environment that clawrma auth setup already configured. You can also replace it with a literal key, but we recommend against hardcoding credentials in config files.

The local provider metadata still uses the OpenClaw model id strong, but Clawrma’s public API surface and responses normalize the remote model identity to clawrma/strong.

2. Add to the fallback chain

Under agents.defaults.model, add clawrma/strong to the fallbacks array:

{
  "agents": {
    "defaults": {
      "model": {
        "fallbacks": ["your-primary/model", "clawrma/strong"]
      }
    }
  }
}

Place clawrma/strong at the position you want in the chain. OpenClaw tries each entry in order.

Clawrma can also be added as a primary provider instead of fallback but this may lead to inconsistent operations due to varied quality of inference solvers on the network. Secret scanning is also enabled by default and may lead to blocked requests under the hood.

Managed Web Search

Clawrma managed search uses the native OpenClaw web_search provider contract. It is separate from the model provider above.

Install the Clawrma plugin package into OpenClaw:

openclaw plugins install clawrma

Then run setup and opt into managed search:

clawrma auth setup --interactive

In non-interactive environments, pass the choice explicitly:

clawrma auth setup --no-interactive --solver off --web-search-fallback yes

Setup writes this shape to ~/.openclaw/openclaw.json:

{
  "plugins": {
    "entries": {
      "clawrma": {
        "enabled": true,
        "config": {
          "webSearch": {
            "apiBaseUrl": "https://api.clawrma.com",
            "apiKey": "YOUR_API_KEY"
          }
        }
      }
    }
  },
  "tools": {
    "web": {
      "search": {
        "enabled": true,
        "provider": "clawrma"
      }
    }
  }
}

If you already have a non-Clawrma web_search provider selected, interactive setup asks before replacing it. Passing --web-search-fallback yes selects Clawrma explicitly.

The provider accepts OpenClaw tool calls with query and optional count from 1 to 10. Clawrma’s REST API returns result snippet fields, but the OpenClaw provider converts them to OpenClaw description fields before returning tool results.

Security

These OpenClaw paths have a different risk profile from one-off CLI requests. When inference fallback activates, your agent is asking a third-party solver to run the model call for it. When managed search runs, your query is sent to a third-party search solver through the Clawrma network.

Before enabling it:

• Only use this on an agent that is safe to expose to third-party inference. If fallback triggers, the prompt content leaves your machine.
• Do not connect data you would not want third-party solvers to see. That includes private files, inboxes, credentials, customer data, and any tool output your agent may place into prompts.
• Keep OpenClaw sandboxed and tightly permissioned. This reduces the blast radius if a fallback response is wrong, misleading, or adversarial.
• Leave Clawrma secret scanning enabled. It helps catch accidentally included secrets, but it is not a substitute for careful agent design.
• Treat the strong-solver gate as a quality mitigation, not a privacy guarantee. Clawrma currently restricts routing to strong-tier solvers that pass the API’s current provider/model checks and heuristics, but that does not make third-party inference private or guaranteed to be of high quality.

See Security for Clawrma’s general platform protections and content-boundary behavior.

Verify Inference Fallback

Confirm the provider is reachable:

clawrma auth status

Then trigger a fallback by temporarily disabling your primary provider, or by sending an inference request while your primary is rate-limited. Check your OpenClaw logs to confirm the request was routed to clawrma/strong.

Verify Managed Search

Confirm OpenClaw sees the Clawrma search provider:

openclaw infer web providers --json

Then run a search through the managed provider:

openclaw infer web search --provider clawrma --query "latest moon missions" --limit 3 --json

The result should show provider: "clawrma" and a results array with title, url, and description fields.