WikiBrainHelpSign in← Home
Help · 4 / 5

Plans and support

Pricing, FAQ, contact

Plans and pricing

When the trial ends you drop to Free automatically; to upgrade, open Settings → Plan → Upgrade to Pro. Checkout is handled by Paddle (our merchant of record), prices are shown with tax for your location, and invoices, payment method and cancellation live under Manage subscription. The subscription pays for an always-on knowledge base that any agent can read and write: hosting, import, bibliography, versions, OAuth connections, Zotero, usable from a phone browser; offline copies and backup mirrors are planned. Model costs are not included: you use your own API key and pay your provider directly; Settings and Stats show real tokens and an estimated cost per job (estimated with OpenRouter's price list; your provider's bill is authoritative). Cursor users need no key at all.

One "agent run" = one ingest, one chat reply, or one deep lint.

PlanTerm and priceWhat you get
Pro trial14 days from sign-up, free, no cardEverything in Pro; unlimited agent runs; the first 10 runs on us (a cheaper model; content goes through the platform's OpenRouter account), no API key needed
FreeFree forever20 agent runs per month; 200 notes, 20 MB, 1 token, 7-day version history; bring your own key
ProUSD 6 per month or 60 per yearUnlimited agent runs; 10,000 notes, 1 GB, 90-day version history; multiple tokens
Self-hostedFree (AGPL-3.0)docker compose brings up Postgres and the service, same code (built-in browser included); you supply the encryption key; Google sign-in, mail and the no-key trial are optional; plan limits are adjustable with environment variables

Limits only block additions: at the note or storage limit you cannot add or grow pages, but reading, shrinking, archiving and export keep working and nothing is deleted or altered. Version snapshots are kept 7 days on Free and 90 days on Pro and during the trial; the latest version of every page is kept forever. The plan card in Settings shows current usage.

FAQ

Pasting a URL says it can't extract the article?
The page most likely has a bot check or needs a login; JavaScript-rendered pages are already retried with the built-in browser. If it still fails, copy the text and use Paste text, or upload a PDF. Paper pages with a DOI keep their bibliography even when the body can't be fetched. Login-only platforms such as Facebook can't be fetched; paste the text instead.
Auto-ingest failed?
The progress panel shows why. The most common cause is the model being rate-limited upstream; the system retries three times automatically. Models on free shared quotas hit this especially often, and switching to a paid model is much more stable. Pages already created are kept.
Which language does the agent write in?
It follows the workspace language (changeable in Settings); schema rules can override it, e.g. "summaries in English, my comments in Chinese". Content can be in any language.
Will Cursor and the web fight?
No. When the same page is edited from both sides, the later writer receives the current version and is asked to edit again; the agent knows this rule too.
The agent got it wrong?
See Rules and templates: fix or roll back the page, correct it in chat, or write the rule into schema/.
No Cursor and no API key?
The first 10 trial runs are on us; afterwards create an OpenRouter key (a few minutes) or connect through Claude.ai's or ChatGPT's connectors.

Contact and reporting problems

Support: hello@wikibrain.app (usually answered within one or two working days). Bugs and feature requests are also welcome as issues on GitHub. Legal: Privacy Policy, Terms of Service. Data is hosted in Singapore (Railway); see section 4 of the privacy policy.