See any repo the way your AI shouldPackage a repo.
Package a repo.
Get its boarding pass.
Paste any public GitHub repo. Carto maps its architecture and hands back a shareable boarding pass: domains, a live dependency graph, and the one thing other analyzers miss: what breaks before you change it.
No install
runs in your browser
No account
paste a URL, that's it
Parsed, never run
tree-sitter, static only
Cached by digest
same commit, instant
WHY A BOARDING PASS
Your AI stops re-indexing
Every tool re-reads the whole repo each session. The boarding pass is the map it should start from, built once, read in seconds.
Blast radius, not just structure
gitdiagram shows you the shape. Carto shows you the consequences: touch one file, see exactly what breaks across domains.
Shareable proof
Drop the badge in your README or share the link. One screenshot says more about your architecture than a paragraph.
[ BEFORE YOU PASTE A REPO ]
The short answers.
01So it's just shared context across my AI tools?
No, that's the least of it. Carto is the layer between your codebase and your AI. Your repo becomes a portable container that sits in the path: every change your AI tool proposes passes through it, gets graded, and the dangerous ones are blocked before they reach disk. A plain index is passive context you hope the AI reads. Carto is context that pushes back.
02I already use Cursor or Copilot. What does Carto add?
They each build their own index of your repo and throw it away when the tab closes. Carto packages the repo once into a container every tool shares, so your AI starts each session already knowing your architecture, blast radius and past decisions, instead of re-reading 40 files to guess.
03Can it actually stop my AI from making a risky change?
Yes. Carto grades every diff your AI proposes for risk and boundary violations before you ever see it, and the MCP middleware can block a HIGH-risk edit before it reaches disk. It's a guardrail that pushes back, not a report you read after the damage is done.
04How is this different from my tests and linter?
Tests catch broken behavior. Linters catch broken syntax. Neither sees what a change did to the shape of your system. Carto shows the blast radius: touch one file and it names the files that break, transitively, before the diff lands.
05Does it remember what we decided last week?
Yes. Every decision and validated diff is saved in one local SQLite file. Ask “did we agree on snake_case here?” six weeks later and you get the actual verdict, not a fresh guess. The container gets smarter the longer the repo lives.
06What exactly is a boarding pass?
It is Carto's one-page container for a repo: its archetype, a structural grade, the worst blast radius, cross-domain coupling, domains and predictive risk. The same container your AI reads so it knows what breaks before it edits.
07Is this my repo's real data?
The featured repos (supabase, next.js, react) show real Carto output. Any other repo you paste renders a representative preview of the boarding pass so you can see the format. For verified numbers on your own repo, run carto init locally. Live web parsing is on the way.
08Does Carto run or store my code?
No. Carto parses source statically with tree-sitter and never executes it. The CLI is local-only: one SQLite file on your disk, no cloud, no account, no telemetry. .cartoignore blocks .env and credential files by default.
09How do I get a boarding pass for my own repo?
npm i -g carto-md, then carto init in your project. Carto builds the container and wires into your AI tools. You can also paste any public GitHub repo above to preview the format first.
10What is the README badge?
A live boarding-pass image you embed in your README. It renders your repo's pass and links back to the full page, so anyone browsing the repo sees its architecture at a glance.
11How much does it cost?
Free. MIT-licensed, one SQLite file, no cloud bill. That's the whole pricing page.