AIOps Bot Platform
Console

Introduction

A two-part platform — a hosted control plane and a runtime binary you run yourself.

Welcome to the docs. The platform is made of two parts that work together:

  • The control plane (this dashboard) — sign in with W3 ID, create projects and agents, upload workspace files, and manage how LLM requests are routed. It also acts as an authenticated proxy for LLM calls, so model API keys never leave the control plane.
  • The runtime (bot-agent) — a standalone binary you download and run yourself on your own machine, server, or container. It handles conversations, tool execution (shell, browser, cron), scheduling, and persistence. Your application talks to it over a local HTTP and WebSocket API.
Your application
  │
  ├── calls ──→ bot-agent (you host it, you run it)
  │               │
  │               └── calls ──→ control plane /api/runtime/*
  │                               (LLM proxy + workspace)
  │
  └── manages ──→ dashboard (projects, agents, files, users)

How the pieces fit

You do…Where it happens
Create projects, agents, membersDashboard
Upload workspace files / AGENTS.mdDashboard (project files)
Download the runtime binaryDashboard (agent page)
Run the agent processYour infrastructure
Send messages, stream responsesYour app → bot-agent
Route LLM calls to vLLM backendsControl plane (automatic)

The control plane never starts, stops, or proxies to the runtime. You own the runtime process entirely. It calls back to the control plane only for LLM access and workspace content.

Where to go next

If you want to…Read this
Ship your first agentGetting started
Understand the runtime modelArchitecture
Run the binary in productionDeployment
Keep tokens & keys safeSecurity
Manage reusable credentialsSecrets & Vaults
How model routing worksModels & routing
Integrate with the HTTP APIAgent API: Getting started