GoModel
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.
- stars
- 1,166
- 30-day movement
- +3211/day
- Related entries
- 61
- Connections
- 3
GoModel is an AI gateway, control plane, and proxy written in Go that exposes a unified OpenAI-compatible and Anthropic-compatible API across providers like OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, and vLLM. It is positioned as a LiteLLM alternative and includes observability, guardrails, streaming, cost tracking, intelligent routing, sticky sessions, failover, real-time logs, and usage tracking.
Reach for it when you need a single Go-based proxy to route, monitor, and control LLM traffic across multiple providers behind one compatible API.
Use it to
- Proxy multiple LLM providers behind one OpenAI-compatible API
- Track token usage and costs per request
- Set up failover and intelligent routing between providers
- Apply guardrails and inspect real-time request logs
- Deploy with Docker using the provided toolchain
For Teams running LLM applications in production
- Role
- mcp-server
- Language
- Go
- Licence
- MIT
- Forks
- 101
- Open issues
- 51
- Last push
- 2026-09-17
- Latest release
- v0.1.0 · 2026-01-03