agent-gateway

mcp
Security Audit
Pass
Health Pass
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 19 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Self-hosted AI gateway for governed LLM, MCP, ACP, and A2A traffic

README.md

Agent Gateway

English | 简体中文

Run and govern Codex, OpenCode, A2A agents, LLMs, and MCP tools through one
self-hosted gateway.

Agent Gateway lets teams expose compatible existing agents as authenticated
internal APIs and gives their model and tool traffic the same control point for
routing, credentials, limits, configuration, and telemetry. Run Codex or
OpenCode through ACP, connect remote A2A Protocol 1.0 agents, host
configuration-defined builtin agents, and expose OpenAI-, Anthropic-, Claude
Code-, and MCP-compatible endpoints.

agent-gateway is the Apache-2.0 gateway engine behind
AgentGuide. It governs agents from the outside; it
is not an Agent framework or a durable workflow engine.

Website · Documentation ·
Install ·
Evaluated capabilities ·
Releases ·
Support

Try it without a provider key

The shortest supported evaluation path needs Docker Engine with Compose v2,
curl, and tar. It downloads a checksummed Compose project, starts the
gateway and a deterministic development fixture, applies a Bundle, and sends
governed Agent requests. It needs no repository checkout, local Go toolchain,
or LLM provider credential.

curl -LO https://github.com/agent-guide/agent-gateway/releases/download/v0.7.1/agent-gateway-first-run-v0.7.1.tar.gz
curl -LO https://github.com/agent-guide/agent-gateway/releases/download/v0.7.1/SHA256SUMS

Verify the archive on Linux:

grep 'agent-gateway-first-run-v0.7.1.tar.gz' SHA256SUMS | sha256sum -c -

On macOS, use shasum -a 256 -c - instead of sha256sum -c -. Then start
the project and run the smoke test:

tar -xzf agent-gateway-first-run-v0.7.1.tar.gz
cd agent-gateway-first-run-v0.7.1
./setup.sh
./run-smoke.sh

A successful run ends with:

Common Agent turn, native A2A ingress, VirtualKey enforcement, interaction persistence, and request metrics passed.

This proves:

  • rejection of an Agent turn without its VirtualKey;
  • a protected common Agent turn over SSE;
  • public native A2A Card discovery and governed JSON-RPC ingress;
  • persisted interaction lookup; and
  • an incremented Prometheus request counter.

Run ./start-observability.sh to add the evaluation-only Prometheus, Tempo,
OpenTelemetry Collector, and Grafana profile. The fixture and anonymous local
Grafana access are for evaluation, not production. See the
first-run guide for prerequisites, reset
commands, and exact boundaries.

Why Agent Gateway

Teams can usually start one Agent. The harder operational problem is giving
many users and Agents a shared boundary without losing identity, policy, or
evidence as traffic crosses Agent, model, and tool protocols.

Need Gateway boundary
Expose existing Agents as internal services Unified AgentRoutes, VirtualKey authentication, streaming turns, cancellation, permissions, sessions, and transcripts where the runtime supports them
Govern model and tool access OpenAI-, Anthropic-, and Claude Code-compatible LLM routes plus managed MCP services and routes
Connect remote Agents Common-turn translation and governed native A2A Protocol 1.0 JSON-RPC ingress
Operate one configuration surface SQLite-backed Admin API, declarative Bundle validate/apply/export, and idempotent updates
Inspect what happened Persisted interactions, per-protocol metrics, Prometheus counters, and optional OpenTelemetry traces
Keep the control point private Self-hosted Caddy-based or standalone runtime with operator-owned storage and deployment authentication

This focus is intentionally narrower than a general Agent SDK or a hosted AI
platform. Agent Gateway supplies the runtime boundary; your applications,
Agents, providers, MCP servers, and any durable business workflow engine remain
separate systems.

Agent integration paths

Path Use it for What you bring
ACP Drive Codex or OpenCode as a protected internal Agent API An external ACP adapter, workspace, and its upstream authentication
HTTP/A2A Connect an Agent implemented in any stack A remote A2A Protocol 1.0 Agent Card and service
Builtin Materialize configuration-defined Agents in process A gateway LLM route, optional managed MCP tools, and a supported eino ADK topology

Claude Code uses the gateway differently: it is a client of the dedicated cc
Anthropic Messages ingress profile, not an ACP Agent runtime. That profile can
route Claude Code traffic to compatible domestic or international model
providers.

Architecture

Agent Gateway architecture overview

The gateway exposes two directions of traffic:

  • Agent Control API (Agent / ACP / HTTP / A2A) — consumers launch and drive
    Agents through protected routes.
  • Resource Access API (LLM / MCP) — applications and Agents reach models
    and tools through governed routes.

A request can enter through an AgentRoute, execute through the selected ACP,
builtin, or HTTP runtime, and call back through LLM or MCP routes. VirtualKeys,
routing, configuration, and telemetry apply at the relevant boundaries. See
the architecture overview for the
runtime flow and dependency boundaries.

Choose your starting point

Goal Start here Additional requirement
Verify a governed Agent request Provider-key-free first run Docker Compose only
Evaluate Codex or OpenCode Coding Agent evaluation External ACP adapter, workspace, and upstream authentication
Connect a remote A2A Agent HTTP Agent quick start An A2A Protocol 1.0 service, or the local fixture
Route OpenAI, Anthropic, or Claude Code traffic LLM quick start A compatible provider and credential
Govern MCP tools MCP quick start A Streamable HTTP or stdio MCP service

What ships

  • Agent runtimes: native ACP pooling and lifecycle management, an in-process
    eino ADK host for builtin Agents, and HTTP/A2A translation and native ingress.
  • Resource gateways: direct-provider or logical-model LLM routing, MCP
    discovery and execution, credentials, VirtualKeys, and per-domain admission
    limits.
  • Operations: SQLite persistence, Admin APIs, declarative Bundles, durable
    usage events, interaction views, Prometheus metrics, and optional OTLP export.
  • Ingress profiles: OpenAI-compatible, Anthropic Messages, the separate
    Claude Code-compatible cc profile, MCP, common Agent turns, and A2A Protocol
    1.0 JSON-RPC.
  • Distribution modes: agw for the Caddy-based runtime, agwd for the
    standalone daemon, and agwctl for management and validation.

Provider implementations and protocol fidelity vary by upstream. Check the
provider guide,
provider option reference, and
evaluated capability matrix before choosing a
production path.

Current boundaries

  • The Community limiter is process-local; a production distributed limiter and
    multi-node HA coordination are not included.
  • Memory, durable workflows, schedules, durable human Tasks, enterprise IAM/SSO,
    organization roles, cost budgets, and a durable compliance audit ledger are
    not implemented.
  • Interactive Agent tool permission decisions are implemented, but they are not
    a general human-task workflow system.
  • ACP execution requires a separately supplied Codex or OpenCode adapter,
    workspace, and upstream authentication.
  • OAuth refresh requires the separately installed agw-auth command or a
    compatible external refresher.
  • Operational events and traces provide telemetry; they are not a compliance
    record.

The evaluated capability matrix separates
implemented, externally dependent, and roadmap behavior. Roadmap capabilities
are not presented as shipped features.

Install and operate

Published release archives support Linux and macOS on amd64 and arm64. The
release installation guide covers checksums,
container images, runtime identity, persistence, and shutdown behavior.

To build all three binaries from source:

make build

The binaries have separate roles:

Binary Role
agw Caddy-based gateway runtime; retains standard Caddy commands such as run, reload, validate, and hash-password
agwd Standalone gateway daemon backed by the shared config store
agwctl Management CLI for Bundle validation/apply/export and Admin operations

Use the Bundle guide for dynamic configuration,
the Caddyfile reference for the Caddy
runtime, and the runtime modes reference to
choose between agw and agwd.

Documentation

Upgrading

v0.7.1 adds no protocol or persisted-resource migration beyond v0.7.0. Stores
that have not completed the external CLI-auth cutover documented since v0.5.0
need a one-time credential migration and a separately installed refresh
command. Do not start an upgrade until you have reviewed the applicable
upgrade guide and rollback preparation.

Community and license

Use GitHub Issues for
reproducible defects, provider compatibility reports, feature proposals, and
documentation gaps. Do not include credentials, private prompts, or private
configuration. Report suspected vulnerabilities through the private process in
SECURITY.md.

Contributions are welcome; start with CONTRIBUTING.md.
Agent Gateway is licensed under Apache License 2.0.

Reviews (0)

No results found