# inference-gateway

> Self-hosted gateway that routes requests to 16+ LLM providers through a single OpenAI-compatible endpoint with MCP tools, A2A agents, guardrails, and observability.

- **Category:** API Gateway
- **Licence:** Apache-2.0
- **Latest version:** v0.60.1
- **Open source:** oss
- **Languages:** Go
- **Platforms:** Docker, Docker Compose, Kubernetes, Linux
- **Tags:** API, Proxy, Mcp, Gateway, Performance, LLM, Anthropic, Openai, Proxy Server, OIDC, Opentelemetry, Kubernetes, Docker, Golang, Tracing, Self Hosted, A2a, Openai compatible, Llm gateway, Guardrails, Opensource, Agnostic, Gateway Api, Inference Api, Opensource Projects, Deepseek V4 Pro, Open Telemetry, Apache 2

## Description

Inference Gateway is a cloud-native proxy server providing a unified OpenAI-compatible API for multiple LLM providers. It supports many providers including major cloud services and local solutions. The gateway adds Model Context Protocol (MCP) integration for automatic tool discovery, Agent-to-Agent (A2A) server for agent coordination, OPA/Rego guardrails for request filtering, OIDC authentication, and OpenTelemetry metrics. Deployment options include Docker, Docker Compose, Kubernetes with an Operator, or a standalone binary. The project is Apache-2.0 licensed with a lightweight ~10MB binary.

## Links

- [Homepage](https://github.com/inference-gateway/inference-gateway)
- [Website](https://docs.inference-gateway.com)
- [Docker](ghcr.io/inference-gateway/inference-gateway)
- [GitHub Repository](https://github.com/inference-gateway/inference-gateway)
- [GitHub Discussions](https://github.com/orgs/inference-gateway/discussions)
- [GitHub Issues](https://github.com/inference-gateway/inference-gateway/issues)

---
Source: https://selfhost.directory/project/inference-gateway