OpenClaw

OpenClaw Foundation. Existing site notes; docs checked previously. Re-verify attach keys on the live docs.

Self-hosted multi-channel gateway (Discord, Telegram, Slack, …) in front of a swappable /v1.

What it’s for

Message the home agent from apps you already use. Already documented on this site.

Local endpoint

llama-server base: http://127.0.0.1:8080/v1
Strata base: http://127.0.0.1:8083/v1
Model name: provider model id in ~/.openclaw/openclaw.json
API key: VLLM_API_KEY even if dummy for vLLM; llama.cpp optional

Tool calling

Channel tools + whatever the model supports. Follow OpenClaw allowlists — do not bind to the internet for a first test.

Long context

Server -c.

ROCm / Radeon gotchas

You own the server. Official Ollama ROCm is not the gfx1201 daily driver.

Hybrid local + cloud

Models are swappable; cloud and local providers are the point of the gateway.

This is the same question as the calculator’sfully localversushybridtoggle. This page does not quote cloud prices.

Official links

Sources

Copy-paste

More on the connect page. Prove http://127.0.0.1:8080/v1/models first.

OpenClaw → llama-server :8080~/.openclaw/openclaw.json

# ~/.openclaw/openclaw.json — attach keys from our earlier notes; re-check live docs.
{
  "models": {
    "providers": {
      "llama": {
        "baseUrl": "http://127.0.0.1:8080/v1",
        "apiKey": "local-not-a-secret",
        "models": [{ "id": "qwen" }]
      }
    }
  }
}
# vLLM path (different port): openai-completions at http://127.0.0.1:8000/v1
# Set VLLM_API_KEY even if dummy. Follow OpenClaw allowlists — do not bind to the internet for a first test.

Exact llama-server flags for our daily driver stay TODO in stacks.yaml. This is the port only. Exact JSON shape: re-verify attach keys on https://docs.openclaw.ai/

OpenClaw → Strata :8083~/.openclaw/openclaw.json

# ~/.openclaw/openclaw.json — attach keys from our earlier notes; re-check live docs.
{
  "models": {
    "providers": {
      "llama": {
        "baseUrl": "http://127.0.0.1:8083/v1",
        "apiKey": "local-not-a-secret",
        "models": [{ "id": "qwen" }]
      }
    }
  }
}
# vLLM path (different port): openai-completions at http://127.0.0.1:8000/v1
# Set VLLM_API_KEY even if dummy. Follow OpenClaw allowlists — do not bind to the internet for a first test.

Exact Strata flags for our rig stay TODO in stacks.yaml. This is the port only. Exact JSON shape: re-verify attach keys on https://docs.openclaw.ai/