OpenClaw Integration

Complete OpenClaw setup guide with model switching, failover, skills, plugins, and troubleshooting for OneInfer.

This page follows the full OpenClaw flow from the reference guide and adapts key/provider settings for OneInfer.

Installing and Configuring OpenClaw

1. Get API key

  • Create or sign in to your OneInfer account.
  • Create an API key from the API keys section.
  • Make sure your account has an active plan or credits.

2. Install OpenClaw

Prerequisite: Node.js 22 or newer.

Installer script (recommended)

bash
# macOS/Linux
curl -fsSL https://openclaw.ai/install.sh | bash

# Windows (PowerShell)
iwr -useb https://openclaw.ai/install.ps1 | iex
OpenClaw installer output

Global install (manual)

bash
npm install -g openclaw@latest

# or with pnpm (recommended)
pnpm add -g openclaw@latest
pnpm approve-builds -g

3. Setup OpenClaw

If onboarding does not auto-start:

bash
openclaw onboard --install-daemon

# If already initialized:
openclaw config
  • I understand this is powerful and inherently risky. Continue? → Yes
  • Onboarding mode → Quick Start
  • Model/auth provider → OpenAI-compatible / Custom

4. Configure OneInfer provider

Use your OneInfer API key and OneInfer OpenAI-compatible endpoint:

json
{
  "env": {
    "OPENAI_BASE_URL": "https://api.oneinfer.ai/v1",
    "OPENAI_API_KEY": "<ONEINFER_API_KEY>"
  }
}

5. Complete setup

  • Select and configure required channels.
  • Configure skills as needed.
  • Finish onboarding.

6. Interact with your bot

Choose Hatch in TUI when prompted, then start chatting in terminal UI.

7. After install

bash
openclaw --version
openclaw doctor
openclaw status
openclaw dashboard

Switching model

If provider model selection does not switch correctly, edit ~/.openclaw/openclaw.json and set your desired default model.

json
{
  "agents": {
    "defaults": {
      "model": {
        "primary": "openai/gpt-4o-mini",
        "fallbacks": ["openai/gpt-4.1-mini"]
      },
      "models": {
        "openai/gpt-4o-mini": {},
        "openai/gpt-4.1-mini": {}
      }
    }
  }
}
bash
openclaw gateway restart
openclaw tui

Advanced configuration

Model failover

json
{
  "agents": {
    "defaults": {
      "model": {
        "primary": "openai/gpt-4o-mini",
        "fallbacks": ["openai/gpt-4.1-mini", "openai/gpt-4o-mini"]
      }
    }
  }
}

Skills with ClawHub

bash
npm i -g clawhub
clawhub search "postgres backups"
clawhub install my-skill-pack
clawhub update --all

Plugins

bash
openclaw plugins list
openclaw plugins install @openclaw/voice-call
openclaw gateway restart

Troubleshooting

Common issues

  • API key authentication: verify key validity and active credits/plan.
  • Model availability: confirm model name and regional availability.
  • Connection issues: verify gateway status and network access.

Resources

  • OpenClaw docs: docs.openclaw.ai
  • OpenClaw GitHub: github.com/openclaw/openclaw
  • OneInfer docs: oneinfer.ai/docs