How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

google-search - Skill - OpenSmartRoute

Skillv1.0.0

google-search

Name: google-search
Author: sundial-org

Search the web using Google Custom Search Engine (PSE). Use this when you need live information, documentation, or to research topics and the built-in web_search is unavailable.

by sundial-org(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from sundial-org/awesome-openclaw-skills (skills/google-search/SKILL.md). Install upstream with npx skills add sundial-org/awesome-openclaw-skills --skill google-search. Copyright stays with the author.

Google Search Skill

This skill allows OpenClaw agents to perform web searches via Google's Custom Search API (PSE).

Setup

Google Cloud Console: Create a project and enable the "Custom Search API".
API Key: Generate an API Key.
Search Engine ID (CX): Create a Programmable Search Engine at cse.google.com, and get your CX ID.
Environment: Store your credentials in a .env file in your workspace:
```
GOOGLE_API_KEY=your_key_here
GOOGLE_CSE_ID=your_cx_id_here
```

Workflow

... (rest of file)

Example Usage

GOOGLE_API_KEY=xxx GOOGLE_CSE_ID=yyy python3 skills/google-search/scripts/search.py "OpenClaw documentation"

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

Installed into a catalogue, chosen by a router

Install google-search and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
When a provider is down or over quota the request moves on; the trace says it did.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

sundial-org-awesome-openclaw-skills-google-search.ocm.jsonjson

{
  "ocm": "1",
  "id": "sundial-org-awesome-openclaw-skills-google-search",
  "kind": "skill",
  "name": "google-search",
  "description": "Search the web using Google Custom Search Engine (PSE). Use this when you need live information, documentation, or to research topics and the built-in web_search is unavailable.",
  "publisher": "sundial-org",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "coding"
    ],
    "tags": [
      "skill-md",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Search the web using Google Custom Search Engine (PSE). Use this when you need live information, documentation, or to research topics and the built-in web_search is unavailable."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/sundial-org/awesome-openclaw-skills",
      "path": "skills/google-search/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/sundial-org/awesome-openclaw-skills/blob/HEAD/skills/google-search/SKILL.md",
      "key": "sundial-org/awesome-openclaw-skills/skills/google-search/SKILL.md"
    }
  },
  "instructions": "# Google Search Skill\n\nThis skill allows OpenClaw agents to perform web searches via Google's Custom Search API (PSE).\n\n## Setup\n\n1.  **Google Cloud Console:** Create a project and enable the \"Custom Search API\".\n2.  **API Key:** Generate an API Key.\n3.  **Search Engine ID (CX):** Create a Programmable Search Engine at [cse.google.com](https://cse.google.com/cse/all), and get your CX ID.\n4.  **Environment:** Store your credentials in a `.env` file in your workspace:\n    ```\n    GOOGLE_API_KEY=your_key_here\n    GOOGLE_CSE_ID=your_cx_id_here\n    ```\n\n## Workflow\n... (rest of file)\n\n## Example Us",
  "cost": {
    "context_tokens": 181
  }
}

Fetch it by URL: GET /api/v1/registry/sundial-org-awesome-openclaw-skills-google-search/manifest?version=1.0.0