You pay per organization per month. All repos within that org get full access. Personal accounts use the Free plan.
Does it work with monorepos?
Yes. Argus reviews the diff of each PR regardless of repo structure. It triages files individually, so large PRs in monorepos still get fast, focused reviews.
What data does Argus store?
PR metadata (title, author, branch), the diff, review comments, and optionally past patterns for memory. We never store your full source code. Diffs are processed in-memory and discarded after review.
Can I use my own LLM API key?
Yes. Configure any OpenAI-compatible provider (OpenRouter, Anthropic, OpenAI, etc.) per pipeline stage from the Settings page. Bring your own key or use ours.
What if Argus flags something incorrectly?
Dismiss it. Each dismissal is stored as a memory with the reason and the kind of change it came from — repeated dismissed patterns stop being posted (security findings are never suppressed). Every comment explains its reasoning, so you can disagree and move on.
Is finding filtering a paid feature?
No. The LLM judge scores every finding on every review, on every plan — low-signal comments are dropped or folded into a collapsed Minor notes section. Pro adds depth (the 4-specialist deep review and Pass 2), not filtering.
Is there a free trial?
All features are free during early access — no trial needed. When paid plans launch, early adopters get a permanent discount.