The control plane for enterprise agent systems

Air-traffic control for your AI agents.

AgentGuide puts every agent, model call, and tool invocation on one radar. Observe everything, govern with policy, and orchestrate fleets of agents that collaborate on real enterprise work — all through a single gateway you run yourself.

live traffic — one control plane Applications Coding CLIs Services Workflows AGENTGUIDE route + virtual keys credential pool builtin agent host policy + limits observe · govern orchestrate usage events + traces LLM providers openai · claude · … MCP tools governed services ACP agents codex · opencode HTTP agents your own services
3agent runtimes — Builtin, ACP, HTTP
10+LLM providers behind one API
8built-in orchestration topologies
100%of traffic attributed to an agent

Why a gateway

Agents are easy to launch. They are hard to run.

Once agents call models, invoke tools, and spawn other agents, nobody can answer the basic questions: what did it cost, who approved that action, which agent broke production? AgentGuide sits on the path of every call and turns agent traffic into something you can see, control, and compose.

Observe

Every call becomes a signed-in event

LLM requests, MCP tool calls, and agent turns are captured as durable usage events — tokens (including cached and reasoning tokens), latency, errors — each attributed to the agent that caused it.

Observability →
Govern

Policy at the gateway, not in every app

Virtual keys for consumers, pooled and scheduled upstream credentials, interactive permission gates for agent actions, recursion-depth limits, and fail-closed concurrency and timeout controls.

Governance →
Orchestrate

Compose agents into real workflows

Run agents inside the gateway with declarative topologies — sequential, parallel, supervisor, plan-execute and more — and coordinate multiple agents on large tasks through shared workspaces and workflows.

Agents & orchestration →

Not another agent framework — AgentGuide orchestrates agents from the outside, whatever they're built with. How it relates to LangGraph, AutoGen & co →

Three runtimes, one identity

Bring the agent you have. Or build it in the gateway.

Every agent — wherever it runs — gets one first-class identity: routes, resources, policy, usage, and health, all managed from a single control plane.

runtime · builtin

Builtin agents

Declared as configuration, materialized inside the gateway — no separate process. The deepest option: inner model calls and tool executions are traced individually, and orchestration topologies are first-class.

runtime · acp

ACP agents

The gateway owns the lifecycle of Agent Client Protocol agents such as Codex and OpenCode: process pooling, sessions and transcripts, streaming turns, and permission decisions routed through your policy.

runtime · http

HTTP agents

Agents that run on their own infrastructure register for identity, routing, and attribution — so external and legacy agents show up on the same radar as everything else.

one agent identity routes resources policy usage health

The flagship: multi-agent collaboration

Workspaces and workflows turn agents into a workforce.

Single agents answer questions. Fleets of agents deliver projects. AgentGuide is built for the second: shared workspaces where agents, models, and tools are assembled per mission, and workflows that schedule multiple agents against one large task — with every step observed and governed.

workspace

Assemble the team

A workspace binds agents to the models, MCP tools, and policies they are allowed to use — a scoped, auditable environment instead of ad-hoc wiring.

workflow

Coordinate the mission

Decompose a large task across agents: plan-execute loops, supervisor delegation, parallel fan-out with synthesis — deterministic control flow over non-deterministic workers.

enterprise

Ship it with confidence

Every hand-off is attributed, every budget enforceable, every permission decision on record. Multi-agent systems your compliance team can sign off on.

The foundation

A serious LLM & MCP gateway underneath.

Orchestration is only as trustworthy as the layer it stands on. AgentGuide ships a production LLM gateway and MCP gateway in the same binary.

llm gateway

One API over every provider

  • OpenAI, Anthropic, Gemini, DeepSeek, Qwen, Zhipu, OpenRouter, Ollama and more
  • OpenAI- and Anthropic-compatible endpoints, plus a Claude Code-ready profile
  • Logical model routing: one model name, many candidate providers, automatic fallback
  • Credential pooling with scheduling — including CLI-auth credentials (Codex, Claude Code, Gemini)
Platform details →
mcp gateway

Tools as governed infrastructure

  • Register MCP services once; expose them through routes with auth policy
  • Tool discovery, execution, and in-flight request inspection
  • Fail-closed tool selection — a missing tool is an error, never a silent skip
  • Every tool call lands in the same attributed event stream
MCP details →

Get started

One binary. Your infrastructure. Full control.

AgentGuide deploys as a single self-hosted binary — no SaaS dependency, no traffic leaving your network except to the providers you choose.