Online 14ms

What can I help with?

AI Assistant

Hello! I'm your AI Agent assistant. Select an agent and describe your task below, and I'll coordinate the agent team to execute it.

You can manage agents, view analytics, configure models, and more from the sidebar.

Model: Auto

Agents

Specialized agents working together on complex tasks.

Token Analytics & Telemetry

Real-time token consumption and cost tracking

Live Telemetry
Total Tokens 21,070 Prompt: 14,250 · Comp: 6,820
Est. Cost $0.052
Avg. Latency 420ms
Total Calls 3

Token Consumption Breakdown

Prompt (Input): 68% Completion (Output): 32%

Recent Execution History

Run ID Time Agent Model Prompt Comp Total Status

Available Inference Models

Discover and select LLM models from your providers

11 Models

System & API Logs Monitor

Real-time tracking of API GET/POST requests, warnings, and error diagnostics

Total Logs 0 All system & API events
API Success (200 OK) 0 GET / POST Succeeded
Warnings 0 Client 4xx / missing configs
Errors 0 5xx & LLM API failures
Time Level Method Endpoint Status Latency Message / Activity Details Details
Loading live operational logs...

API Provider & Configuration

Manage your LLM provider connections and API keys

LLM Provider

Choose the provider and model AgentOS will use.

Not connected
General-purpose models with strong tool support.
Leave empty to use the provider default.
No API key configured

Connection

Current provider connection status.

Status Not configured
Provider —
Model —
API Key Not configured
Last verified —