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.
Tools I use:
- HeyGen (https://www.heygen.com/?sid=rewardful&via=whoffagents) — AI avatar videos
- n8n (https://n8n.io) — workflow automation
- Claude Code (https://claude.ai/code) — AI coding agent
My products: whoffagents.com (https://whoffagents.com?ref=devto-3508364)
