wikipilot scans your codebase and generates a wiki where every page tracks its own source files — so when the code changes, the docs tell you instead of quietly going stale.
Docs get written once. The code they describe keeps changing forever.
Nothing tells you which pages are still true and which nobody's touched since the feature they describe got rewritten.
By the time someone notices, they've already shipped the wrong instructions.
wikipilot reads your repo's structure and source content — no config, no annotations required to get started.
Every page is written with a record of exactly which source files it came from and when.
When those source files change, the page flips to "may be outdated." You see it before your reader does.
Every page tracks the exact source files it was generated from and when. Change the code without regenerating the page and it marks itself stale — so the next person finds out from the wiki, not from you in Slack.
Grounded only in what's actually in your wiki. Ask it something that isn't documented and it says so, not a confident guess.
Client-side, no server or index to run. Works even on a plain static host.
Architecture and flow diagrams render straight from fenced code blocks in your Markdown. One less tab open.
wikipilot init drops a Claude Code skill into your repo, so keeping the wiki in sync is a prompt away — not a recurring task nobody owns.
Build once, get plain HTML/CSS/JS back. Put it in a bucket, a Pages project, wherever — there's no backend to keep alive.
sources — the exact files this page was generated from.
last_synced — the timestamp it was last regenerated against those files.
stale — flips automatically once a source file changes underneath it.
The CLI is MIT licensed and stays that way. Only the hosted tier is a paid product.
Point wikipilot at a repo and see the freshness contract for yourself in under five minutes.