GitHub (Repo to Canvas)

Quality varies by repo size and structure. Feedback welcome at ask@collapseindex.org.

The GitHub tab (H, then GitHub) lets you point at a public or private GitHub repo and have Chinilla AI build a diagram by reading the file tree and config files.

How to use it

1. Open the AI panel with H.
2. Click the GitHub tab.
3. Paste a repo URL (https://github.com/owner/repo) or pick one from your linked repos.
4. Click Analyze Repository (10 credits).

The AI reads the file tree, README, and config files (docker-compose.yml, package.json, pyproject.toml, etc.) to find services, blocks, and how they connect. Source code is not stored. A diagram appears on the canvas when it’s done.

What the AI looks at

• The file tree (folders, file types, languages).
• README.md (first 10,000 characters).
• Manifests: package.json, pyproject.toml, Cargo.toml, go.mod, requirements.txt.
• Container configs: Dockerfile, docker-compose.yml, compose.yaml.
• CI/CD configs: .github/workflows/*.yml.

Source files are never sent to the AI or stored on our servers.

Connecting your GitHub account

To analyze private repos or pick from your repo list, connect your GitHub account:

1. Open the GitHub tab.
2. Click Pick from your repos.
3. Sign in with GitHub.

You can analyze any public repo by URL without connecting an account.

Re-analyzing and auto-check

Once a repo is connected, the panel shows:

• Check for updates (free) — looks for new commits since the last analyze.
• Re-analyze (10 credits) — fresh analysis, updates the diagram.
• Auto-check toggle — checks for new commits when you open the project (max once per 5 minutes per project, always free).

When Check for updates finds new commits, the panel shows a “New changes detected” banner with a one-click Sync now button.

Caching

Re-analyzing the same commit returns the cached result instantly and costs 0 credits. The cache is keyed to the commit, so any new commit means a fresh analysis.

Privacy: the cache is shared across users for public repos only (so two people analyzing the same open-source commit both pay 0 the second time). Private repos are never cached — every re-analyze re-runs the AI and costs 10 credits, but your private code structure is never exposed to other users.

Publishing

Once analyzed, you can publish your diagram as a public link or embed it in your README:

1. In the GitHub panel, toggle Publish diagram on.
2. Copy the public URL, Markdown embed, or iframe embed.

The Markdown embed shows a live PNG of your architecture — great for repo READMEs.

Limits

• Public repos and your connected private repos.
• About 150 files per pass (big repos get a smart pre-pass to pick the most important services).
• 10 credits per analyze.
• Pro plan required.