cd /news/ai-agents/ask-hn-is-anyone-running-ai-agents-i… · home › topics › ai-agents › article
[ARTICLE · art-24771] src=news.ycombinator.com ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Ask HN: Is anyone running AI agents in production reliably – what's your stack?

Several developers report running AI agents in production, with Hermes and Openclaw used for personal projects and Microsoft's Copilot Studio for workplace deployments. IT security policies at work restrict some agent options, limiting deeper implementation. The question highlights ongoing challenges in reliably deploying AI agents across different environments.

read1 min views26 publishedJun 12, 2026

May I ask where? Personal? Work? For personal, try Hermes or Openclaw (I've recently switched to the former). At work, Copilot Studio and copilot cowork agents are as far as I've gotten. Intend to get deeper at work, but IT security policies limit some options. Curious what others are doing.

source & further reading
news.ycombinator.com — original article Show HN: AMD EPYC Windows developer rigs in the UK/EU in ~10 minutes New Python security updates explicitly block the eMudhra certificates by SPKI MCP-warden local credential broker so AI agents never see your secrets
── more in #ai-agents 4 stories · sorted by recency
── more on @hermes 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ask-hn-is-anyone-run…] indexed:0 read:1min 2026-06-12 · —