# ENTERPILOT/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.

Repository: https://github.com/ENTERPILOT/GoModel
Canonical: https://ross.abutalabs.com/products/gomodel
Homepage: https://gomodel.enterpilot.io/?utm_source=github_desc
Language: Go
License: MIT
License Family: permissive
Topics: ai, proxy, ai-gateway, ai-proxy, anthropic, go, golang, groq, llm, llm-gateway, observability, ollama, openai, openai-compatible, openai-compatible-api, openai-compatible-proxy-server, litellm-alternative
Last push: 2026-09-02T21:39:14+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 88, longevity 19
- inputs: {"age_days": 271, "days_push": 0, "days_rel": 0, "gap_med": 1.0, "n_releases_24m": 87}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1107, forks 92 (observed 2026-09-03T02:15:05.699524+00:00)

## What it is
GoModel is an open-source AI gateway and control plane 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 adds observability, response caching, guardrails, cost tracking, intelligent routing, failover, sticky sessions, and real-time usage logs, positioning itself as a production-ready LiteLLM alternative.

## Use cases
- route LLM requests to multiple providers through one OpenAI-compatible endpoint
- track token usage and LLM spending per model, path, or user
- cache identical LLM responses to cut costs and latency
- add guardrails and audit paths to AI traffic
- fail over between LLM providers automatically
- swap model providers without changing application code
- self-host a LiteLLM alternative in Go
- debug AI calls with real-time request logs

## When to choose
- you need a fast, resource-efficient self-hosted AI gateway in Go
- you want provider-agnostic LLM routing with cost tracking and observability
- you want OpenAI and Anthropic SDK compatibility against many backends
- you need caching, guardrails, and failover at the gateway layer

## When to avoid
- you need a client-side SDK embedded in your app rather than a proxy service
- you require a long-proven enterprise gateway with a large community
- your stack is Python-centric and you prefer LiteLLM's Python ecosystem

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, proxy, api-gateway, caching, monitoring, analytics, auth, rate-limiting, logging, middleware
- domain: large-language-models, artificial-intelligence, apis, self-hosted, developer-tools, analytics, backend
- platform: windows, self-hosted, go, cross-platform
- tags: ai-gateway, llm-gateway, ai-proxy, openai-compatible, anthropic-compatible, litellm-alternative, cost-tracking, guardrails, intelligent-routing, failover, usage-tracking, observability, provider-routing, response-caching, ai-agents, linux, macos, docker, web-server

## Member repositories
- ENTERPILOT/GoModel (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:05.699524+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:51:13.197025+00:00, confidence not recorded.
  - readme: https://github.com/ENTERPILOT/GoModel (fetched 2026-09-03T02:15:05.699524+00:00, sha 67687bf84bde)
  - homepage: https://gomodel.enterpilot.io/?utm_source=github_desc (fetched 2026-08-29T12:53:18.870786+00:00, sha 3fa3940dabe7)
  - site_page: https://gomodel.enterpilot.io/docs (fetched 2026-08-29T12:53:18.883110+00:00, sha 97c3d4bdbc26)
  - site_page: https://gomodel.enterpilot.io/ (fetched 2026-08-29T12:53:18.880593+00:00, sha 3fa3940dabe7)
- Data as of 2026-08-30T08:39:29.467469+00:00.