Documentation · Architecture

Same control plane, different products

reading time: 5 minscope: control plane · device daemon · API

The remoteagent architecture separates where the brain lives from where the machine lives. The control plane at remoteagent.online holds identity, keys, budgets and traces; the daemon on your machine holds your files, apps and actions. Nothing runs in the dark.

Control plane (the console)

The console is a Sngine-hosted PHP application with a dedicated mona-plugin. It provides:

Device daemon (the agent)

The open-source client (apps/desktop in MONAEXPERT/agent) runs on macOS, Linux or WSL2. It holds exactly one secret: your Remote Agent key, in a 0600 file. It dials out via HTTPS — no inbound ports, no public IP needed.

API surface

RouteAuthPurpose
/api/v1/mona/*session + CSRFdashboard API: agents, keys, tokens, devices, runs, insights, settings, 2FA
/api/v1/agent/*Bearer (Remote Agent key)device API: verify, think (SSE), tasks, runs, steps, stats, activity
Scope isolation. Device tokens can only reach their own runtime surface. Account-admin and destructive routes (keys, tokens, devices, reset) are dashboard-only — a stolen device key can never wipe a vault. See Security Model.

Run lifecycle

  1. A chat message or queued command creates a task for a device.
  2. The daemon claims the task and streams steps back: think → tool call → tool result → answer → verify.
  3. The console records each step with model, tokens and cost, and links it to the run trace.
  4. You see the whole thing live in the dashboard, Deep Dive and Logs.

Cost & model routing

Every response is price-mapped per model family (exact model → exact price; unknown → flagged estimate). The brain config (auto / cheap / balanced / deep / manual) and per-task complexity profiling decide step budgets and provider preference — simple tasks route to cheap models, complex ones to deep ones.

© 2026 remoteagent.onlineGitHub: docs/ARCHITECTURE.md ↗