Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

agentgateway

agentgateway• Pinned

agentgateway: An open source proxy for AI-native connectivity across agents, LLMs, tools, and external data sources.

What problem it solves

Agentic applications need to communicate securely with LLMs, tools, external data sources, and other agents across different frameworks and environments. Agentgateway provides a central proxy that adds security, observability, and governance to agent-to-LLM, agent-to-tool, and agent-to-agent communication.

Key features

  • Unified LLM Gateway — Route traffic to major LLM providers through a unified OpenAI-compatible API, with controls and policies for traffic management.

    Source: README

  • MCP Tool Connectivity — Connect LLMs with tools and external data through MCP, supporting multiple transports, OpenAPI integration, tool federation, and OAuth authentication.

    Source: README

  • Agent-to-Agent Communication — Support A2A communication with capability discovery, modality negotiation, and task collaboration between agents.

    Source: README, api

  • Policy Enforcement and Guardrails — Apply authentication, authorization, rate limits, and content filtering to control agent traffic and model interactions.

    Source: README

  • Flexible Deployment Options — Deploy as a standalone service or on Kubernetes with a built-in controller, Gateway API support, and a UI for configuring connections and raw YAML.

    Source: README

Who it may suit

This project may suit teams building agentic applications that need centralized connectivity, policy enforcement, and observability for communication with models, tools, data sources, and other agents.

Topics to discuss

  • Which agent-to-LLM, agent-to-tool, or agent-to-agent deployment patterns should receive more documentation and examples?

  • How should CEL policies and guardrails be organized for organizations with multiple environments and teams?

  • What improvements should be prioritized for the standalone CLI, Kubernetes controller, Gateway API integration, and configuration UI?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/agentgateway/agentgateway#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/agentgateway/agentgateway

Comments

…