Install
openclaw skills install ondeckllmLocalhost dashboard for managing LLM providers, model routing, and batting-order fallback chains. Auto-discovers providers from OpenClaw config or works standalone. Use when: (1) user wants to manage or view their LLM providers, (2) user wants to change model priority/batting order, (3) user wants to check provider health or latency, (4) user wants to add/remove/configure LLM providers, (5) user mentions OnDeckLLM or model lineup. Requires: Node.js 22+, OnDeckLLM installed (`npm install -g ondeckllm`).
openclaw skills install ondeckllmnpm install -g ondeckllm
Verify: ondeckllm --help or check install with npm list -g ondeckllm.
OnDeckLLM is a localhost web dashboard that:
~/.openclaw/openclaw.json)# Default port 3900
ondeckllm
# Custom port
PORT=3901 ondeckllm
The dashboard runs at http://localhost:3900 (or custom port).
Use the helper script to check status or start OnDeckLLM:
node scripts/status.js
Output: JSON with running (bool), port, url, and pid if active.
node scripts/status.js
Direct them to http://localhost:3900 (or the configured port/URL).
OnDeckLLM reads provider config from ~/.openclaw/openclaw.json automatically.
Changes made in the dashboard sync back to OpenClaw config.
No separate API or CLI commands needed — it's a web UI tool.
OnDeckLLM stores its data in ~/.ondeckllm/:
config.json — provider settings, port, Ollama URLusage.jsonl — cost tracking logprofiles/ — saved batting-order profilesTo connect to a remote Ollama instance, configure in the dashboard UI:
Settings → Ollama → Remote URL (e.g., http://192.168.55.80:11434)