Repository auditing
Purpose, technology, git history, dependencies, maintenance state, reusable assets and security, from a single agent.
Know what every repository is for before you spend an hour re-learning it.
Read-only AI agents audit a folder of repositories and return one evidence-backed recommendation per repository: continue, archive, delete-candidate or investigate.
Where it is today Working tool, used on our own repositories
Tutorials cloned once, experiments never finished, forks nobody changed, and real projects mixed in among them. Deciding what to keep normally means opening each one and reconstructing its history from memory.
Purpose, technology, git history, dependencies, maintenance state, reusable assets and security, from a single agent.
Architecture, security, cloud and infrastructure-as-code, and testing reviews run only where the repository warrants them.
Observed facts are kept separate from inferences. Each recommendation states its confidence and what could not be determined.
The auditing agents hold no file-write tool. Nothing is archived, deleted, committed or pushed automatically; the decision stays with a person.
For the repositories you decide to continue, a separate agent documents their real conventions so AI coding tools work well in them.
Pick one of four sample repositories and watch the audit reach its recommendation.
$ audit ./terraform-aks-sample
Keep the cluster module as a reusable snippet; archive the repository. Confidence: medium.
Simulated walkthrough with sample data. Nothing here connects to a live system.
Tell us where you are. An engineer replies with a proposal, not a sales script.
All products