OpenClaw on Sideren.

OpenClaw speaks the OpenAI Chat Completions dialect, so it runs on Sideren as a custom provider: the gateway URL (with /v1), your Sideren key, and catalog ids as model ids.

One command

npx sideren setup --tool openclaw --key sdn_your_key

The setup helper registers the Sideren provider for you. See setup helper.

Configure

OpenClaw registers custom providers in ~/.openclaw/openclaw.json under models.providers. Use api: "openai-completions" (openai-responses also works, since the gateway serves /v1/responses):

~/.openclaw/openclaw.json

{
  "models": {
    "providers": {
      "sideren": {
        "api": "openai-completions",
        "baseUrl": "https://api.sideren.io/v1",
        "apiKey": "sdn_your_key",
        "models": [
          { "id": "@sdn/gpt-oss-120b", "name": "Sideren fast" },
          { "id": "@sdn/glm-5", "name": "Sideren coding" }
        ]
      }
    }
  }
}

Then select sideren/@sdn/gpt-oss-120b as your agent model. Keep the provider key (sideren) and the model prefix in sync — a mismatch is the usual cause of a “no API key found” error. The file is JSON5, so you can also add this block in the raw JSON5 editor under Settings → Advanced in the local UI at http://127.0.0.1:18789.

Verify

Send your agent a trivial task and watch it answer on the Sideren model. To confirm the key works against the gateway without OpenClaw in the loop:

npx sideren test --key sdn_your_key

Get started

Agents

API reference

Guides

Reference

OpenClaw on Sideren.

One command

Configure

Verify

​One command

​Configure

​Verify

One command

Configure

Verify