AI-Gateway
Active·★ 1.0k·MIT·Updated 2026-09-16
AI Gateway is an enterprise-grade gateway powered by Azure API Management for managing AI models, tools, and agents. It provides security, performance, observability, cost control, and extensibility. The project includes 30+ hands-on labs to help users deploy and manage AI gateway capabilities in Azure.
#a2a#agents#apimanagement#autogen#azure#foundry#genai#mcp
01
Features
01Security with OAuth 2.0, managed identities, and content safety filtering
02Performance with load balancing, semantic caching, and request routing
03Observability with token metrics, built-in logging, and tracing
04Cost control with rate limiting, quota management, and FinOps framework
05Extensibility with MCP protocol support, function calling, and multi-model routing
02
Compatibility
Azure API Management
Azure APIM
Verified via docs
Python
Python 3.12+
Verified via docs
VS Code
VS Code with Jupyter
Verified via docs
03
Quick start
1
$ git clone https://github.com/Azure-Samples/AI-Gateway.git
2
$ cd AI-Gateway
3
$ code .
04
Use cases
↳Manage and control access to Large Language Models with enterprise-grade policies
↳Enable secure tool access with MCP protocol and function calling
↳Build and control agentic applications with orchestration frameworks
05
Alternatives
DeepMCPAgent★ 892
Model-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.
trpc-agent-go★ 1.9k
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
data-api-builder★ 1.5k
Data API builder provides modern REST, GraphQL endpoints and MCP tools to your Azure Databases and on-prem stores.
Comments
Log in to leave a comment
No comments yet. Be the first!