Route multi-provider LLM traffic through GoModel
Use GoModel as an OpenAI-compatible and Anthropic-compatible gateway for routing, observability, failover, and cost tracking across model providers.
npx skills add agentskillexchange/skills --skill route-multi-provider-llm-traffic-through-gomodel
# Route multi-provider LLM traffic through GoModel
What this skill actually does
Use this skill when an agent team needs controlled model traffic instead of direct provider calls. The operator runs GoModel, configures provider credentials, points OpenAI-compatible or Anthropic-compatible SDK clients at the GoModel endpoint, and validates routing, streaming, observability, failover, sticky sessions, guardrails, and cost tracking from one gateway.
Invoke this for repeatable agent infrastructure work: routing requests across OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM, Bedrock, Azure OpenAI, OpenRouter, and other supported providers; testing provider fallback; inspecting real-time usage logs; or putting spending controls in front of agent workloads.
The scope is the operator workflow of placing agent LLM calls behind GoModel and verifying the gateway path. It is not a general GoModel feature listing, model-provider marketplace, or generic proxy/server card.
Source-backed Docker quick start from the upstream README:
“`bash
docker run –rm -p 8080:8080 \
-e OPENAI_API_KEY=”your-openai-key” \
enterpilot/gomodel
“`
After the gateway is running, open `http://localhost:8080/admin/dashboard`, configure provider keys through environment variables, `.env`, `config.yaml`, or the dashboard, then update the agent SDK base URL to `http://localhost:8080/v1` for OpenAI-compatible clients or `http://localhost:8080` for Anthropic-compatible clients.