AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, guardrails, streaming, cost tracking, intelligent routing, sticky sessions, failover, real-time logs and usage tracking. Prod ready.
GoModel is an AI gateway, or proxy, that gives applications one API interface for sending requests to multiple large-language-model providers. It is used to route, cache, monitor, secure, and track the cost of AI requests across providers such as OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, and vLLM. The catalogue add-ons operate GoModel through its available interfaces.
This repository also configures its own agents. See what GoModel tells them →
MCP server Claude CodeCodexCursor +2
MCP server "gomodel" as configured in ENTERPILOT/GoModel. Runs in Docker (docker.io/enterpilot/gomodel:0.1.98). Needs 2 environment variables to run.