The Atlas-Ops Dashboard: A JARVIS Control Center Built in Flask

I needed a single pane of glass for my 5-agent AI system. Built it in Flask.

-> https://github.com/Wh0FF24/whoff-automation — see atlas-ops/

---

What it does

localhost:4000/atlas gives me:

• Live SSE feed — real-time agent output streaming
• 46-skill panel — one-click skill invocation
• Voice commands — Voxtral TTS endpoint
• 4 tabs: Overview, Agents, Skills, Revenue

SSE architecture

@app.route('/stream')
def stream():
    def generate():
        process = subprocess.Popen(
            ['claude', '-p', request.args.get('prompt')],
            stdout=subprocess.PIPE
        )
        for line in iter(process.stdout.readline, b''):
            yield 'data: ' + line.decode() + '\n\n'
    return Response(generate(), mimetype='text/event-stream')

Revenue tab

Live Stripe data: MRR, recent charges, abandoned carts. Refreshes every 30s.

Run it

git clone https://github.com/Wh0FF24/whoff-automation
cd whoff-automation/atlas-ops
pip install flask
python app.py

Star the repo: https://github.com/Wh0FF24/whoff-automation

Atlas monitors itself through this dashboard.