Project-specific guardrails
Findings are grounded in your real architecture model (layers, import graph, patterns, ADR decisions)—not generic lint rules.
ArchGuard
Architectural review while you write code.
Not a linter. A feedback loop for architecture—so boundaries stay intact as the codebase grows. ArchGuard catches dependency direction violations, boundary leaks, and pattern drift in real-time, grounded in your project’s architecture docs and ADRs.
Quiet by design: Low-confidence findings are dropped. Silence is a feature.
What it does
Defensible explanations
Each finding explains the rule, the evidence, the consequence, and a suggested fix—so teams can align and move fast.
Works where devs already are
Designed for Cursor / VS Code via MCP so it can sit directly in the developer workflow, not as a separate review ritual.
How it works
1. Scan
Builds an architecture model from the repo: layers, dependency direction, patterns, and ADR summaries.
2. Ground
Assembles a project-specific system prompt and schema so findings are anchored in this codebase’s intent.
3. Review
Calls a pluggable AI provider and returns structured findings rendered inline in the IDE.
Principle: pluggable by design
AI providers are adapters. Payments are adapters (Stripe + Bitcoin one-time + Lightning pay‑as‑you‑go planned).
FAQ
Does it send my whole repo?
No. The local scanner builds the model. Reviews send only what’s needed for analysis.
Will it spam warnings?
No. Silence is a signal of health. Low-confidence findings are dropped.
Can we switch AI providers?
Yes. Providers are pluggable behind a stable interface so the system can track a rapidly advancing ecosystem.
How is billing handled?
Subscriptions plus additional integrations: Bitcoin (one-time) and Lightning (pay‑as‑you‑go) planned.
Keep architecture from becoming a post‑mortem topic.
Turn architecture intent into real-time guardrails.