DevTools Dashboard

Real-time agent observability built into every app-mode project.

Quick start

cd my-project-app
agentvoy dev

This starts your agent server with hot-reload and opens the DevTools dashboard at http://localhost:8080/dev.

What you see

Real-time event feed

WebSocket-powered stream showing every agent action as it happens

Event timeline

agent_start, llm_call, tool_call, guard_check, pipeline_stage, agent_complete

Pipeline visualization

See multi-agent stages progress in real time with status bars

Detail inspector

Click any event to see full payload — model, tokens, latency, tool I/O

API Endpoints

Method	Path	Description
GET	/dev	DevTools dashboard UI
WS	/ws/trace	Real-time trace event stream
GET	/dev/events	All events as JSON
POST	/run	Run your agent
GET	/health	Health check

Trace events

All 7 framework adapters are instrumented out of the box. The tracer collects:

Event	Data captured
agent_start	Agent name, prompt, model
llm_call	Model, latency, tokens in/out
tool_call	Tool name, input, output, latency
guard_check	Check type (input/output), pass/fail
pipeline_stage	Stage name, index, status
agent_complete	Agent name, result preview

Using the WebSocket stream

Connect programmatically to receive trace events in real time:

import json
import websockets

async def stream_events():
    async with websockets.connect("ws://localhost:8080/ws/trace") as ws:
        async for message in ws:
            event = json.loads(message)
            print(f"[{event['event']}] {event.get('data', {})}")

Fetch all events as JSON

curl http://localhost:8080/dev/events | python -m json.tool

Enabling tracing

Tracing is enabled by default in app-mode projects. To configure it, edit agent.guard.yml:

observability:
  tracing: true       # Enable/disable tracing
  log_level: info     # debug | info | warn | error
  cost_tracking: true # Track API costs per session