We saved the best for last.
This week we’ve been shipping enterprise-ready features into DevOps Open Agent and one of the biggest asks from teams is simple:
How much are we spending on LLM usage, and can we control it?
When you run AI across investigations, different providers (OpenAI, Anthropic, Gemini, Bedrock, Ollama, and more), that cost adds up fast. For enterprises, this isn’t a nice-to-have. It’s budget.
Today I’m happy to share that DevOps Open Agent now includes a Usage tab where you can:
âś… See token usage and estimated cost across your AI analysis
âś… Break it down by day, agent, and LLM provider
âś… Track cost per investigation, not just overall spend
âś… Set a daily budget and get Slack/Teams alerts when spend crosses your limit
In simple terms: you can finally see what AI is costing you, where that cost is coming from, and get notified before it surprises finance.
We also added editable pricing rates and clearer investigation cost breakdowns, so estimates stay useful as models and prices change.
Open source. Self-hostable. Built for real DevOps teams.
If you’re running AI in production troubleshooting workflows, cost visibility shouldn’t be an afterthought.
đź”— DevOps Open Agent: https://github.com/ideaweaver-ai/devops-open-agent
🎥 YouTube: https://lnkd.in/g2PbG3Hc
Top comments (0)