Few things you wanted to know about how OVYERO works, where your code goes, and what happens when a rule is wrong.
Verdicts come back in about a second. Most engineers don't notice it ran. They only notice when something needs fixing.
No. Ovyero is deterministic, rule-based code: pattern matching, AST analysis, and schema validation. It never calls an LLM and never sends your code to one, so the same input returns the same verdict every time. The only AI involved is your own assistant running on your machine; Ovyero just checks what it wrote. Any semantic evaluation runs client-side with your own AI and your own keys, never through our servers.
At each commit your staged file content is sent to our server over TLS to be evaluated, held in memory only for that evaluation, then discarded. It is never written to disk, databases, backups, or the audit log. We keep only the verdict metadata (rule ID, file path, severity) and a SHA-256 hash of each file, never the code itself.
Not yet. The rule set is curated and maintained by us. Custom rule authoring is on the roadmap. For now, you tune which domains run via your project type.
Language-agnostic where rules are pattern- or AST-based, so it works on any text-based source. Some domains are language-specific, most apply broadly.
There's a bypass flag for genuine emergencies, and every use of it is recorded in the audit log. No silent skips. You can always see what was overridden and by whom.
We want to make Ovyero the best it can be and input from you genuinely helps.
ezra@visnryentertainment.com