“If you give everyone a harness workspace that is great at writing code, you’ll wind up with way more code than you need,” Rhea wrote in his blog post. “The result became a flood of vibe coded apps looking for a problem to solve.”
The growing use of AI agents within the organization also meant “anyone at Cloudflare could now write bad code, faster, thanks to AI,” Rhea said. So the organization created the Cloudflare Engineering Codex, an “authoritative guide” to help both human engineers and AI agents review code and catch potential issues.
Over the past four months, the company’s AI code reviewer “flagged nearly a quarter of a million deviations from Cloudflare engineering standards and blocked 16,000 merges,” said Timo Reimann, a systems engineer at Cloudflare, in a blog post about the Engineering Codex and how the company uses AI agents to uphold engineering standards.
Open source but not free of cost
Now that the company is open-sourcing Cloudflare OS for others to use, developers can try to run the entire stack on their own machines. A notable caveat is that the Cloudflare OS backend can only be deployed by Cloudflare users who have subscribed to the Workers Paid plan.
The paid subscription requirement was not initially made clear up front. A GitHub user raised the issue and shared a screenshot showing that their Workers Free plan had been stopped from deploying the Cloudflare OS backend partway through the process.
“You have a right to charge but requirements should be completed before starting the deployment process,” wrote the GitHub user mac2net. “I wasted 20 minutes I will never get back.”
To Cloudflare’s credit, the company quickly updated the deployment process to alert users at the start about the paid plan requirements. A company representative also responded to the issue on GitHub.