Skip to content
@inference-gateway

Inference Gateway

An open-source, cloud-native, high-performance gateway unifying multiple LLM providers, from local solutions like Ollama to major cloud providers
Inference Gateway Logo

Inference Gateway

An open-source, cloud-native, high-performance gateway unifying multiple LLM providers

GitHub Stars License: MIT Go Docs

📖 Documentation · 🚀 Getting Started · 💬 Discussions · 🐛 Issues


🌐 What is Inference Gateway?

Inference Gateway is a proxy server that provides a unified API to interact with multiple large language model (LLM) providers — from local solutions like Ollama to major cloud providers like OpenAI, Anthropic, Groq, Cohere, Cloudflare, and DeepSeek.

Stop managing multiple SDKs and API keys. Route all your LLM traffic through a single, production-ready gateway.

# One endpoint. Every provider.
curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-4o", "messages": [{"role": "user", "content": "Hello!"}]}'

✨ Key Features

Feature Description
🔀 Unified API One OpenAI-compatible endpoint for all LLM providers
🔌 MCP Integration Native Model Context Protocol support for automatic tool discovery
🤖 A2A Protocol Agent-to-Agent coordination across specialized agents
🌊 Streaming Real-time token streaming from all supported providers
☸️ Kubernetes Ready First-class K8s support with Operator and HPA scaling
📊 Observability OpenTelemetry integration for monitoring and tracing
🔒 Privacy First Self-hosted, zero data collection, MIT licensed
🌿 Lightweight ~10.8MB binary with minimal resource footprint

🏗️ Ecosystem

Core

Repository Description
inference-gateway The core gateway server
operator Kubernetes Operator for lifecycle management
cli Agentic CLI assistant with project context awareness
adl-cli Scaffold and manage A2A-powered enterprise agents

SDKs

Repository Language
sdk Go
rust-sdk Rust

A2A Agents

Repository Description
adk Agent Development Kit for building A2A-compatible agents
google-calendar-agent Google Calendar scheduling & automation
browser-agent Browser automation via Playwright
documentation-agent Context7-style documentation access for agents

🚀 Quick Start

# Run with Docker
docker run -p 8080:8080 \
  -e OPENAI_API_KEY=your-key \
  ghcr.io/inference-gateway/inference-gateway:latest

# Or install the CLI
curl -fsSL https://raw.githubusercontent.com/inference-gateway/cli/main/install.sh | bash
infer init && infer chat

👉 Full setup guide: docs.inference-gateway.com/getting-started


🤝 Contributing

We welcome contributions of all kinds — bug reports, feature requests, documentation improvements, and code!


Released under the MIT License · Built with ❤️ in Go

Pinned Loading

  1. inference-gateway inference-gateway Public

    An open-source, cloud-native, high-performance gateway unifying multiple LLM providers, from local solutions like Ollama to major cloud providers such as OpenAI, Groq, Cohere, Anthropic, Cloudflare…

    Go 104 17

  2. adl-cli adl-cli Public

    A command-line tool to scaffold and manage enterprise-ready AI Agents powered by the A2A (Agent-to-Agent) protocol

    Go 8 2

  3. cli cli Public

    An agentic command-line assistant that writes code, understands project context, and uses tools to perform real tasks.

    Go 2 2

  4. adk adk Public

    An Agent Development Kit (ADK) allowing for seamless creation of A2A-compatible agents written in Go

    Go 19 1

  5. rust-sdk rust-sdk Public

    An SDK written in Rust for the Inference Gateway

    Rust 2 1

  6. sdk sdk Public

    An SDK written in Go for the Inference Gateway

    Go 3

Repositories

Showing 10 of 30 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…