ContextScribe

Privacy Policy

Effective date: 2026-10-30 · This policy applies to the ContextScribe web application and the ContextScribe Chrome extension (together, the “Service”).

We built ContextScribe so researchers keep ownership of their work: your captured pages, notes, memories and research stay yours. This policy explains, plainly, what data the Service handles, why, where it goes, and the controls you have.

1. Who is responsible

ContextScribe is operated by the ContextScribe team (the “operator”). Contact: rafirahman3648@gmail.com

2. Data we handle

Account data — your email address, an optional display name, and a password stored only as a salted scrypt hash. If you sign in through a configured identity provider (Supabase Auth), we store the provider user id linked to your account.
Session data — opaque session tokens are stored only as SHA-256 hashes with expiry; the raw token lives in your browser (httpOnly cookie and/or local storage) and is never kept in plaintext server-side.
Your content — everything you create or capture: projects, sources (page URL, domain, extracted text), pasted text, uploaded files (.txt, .md, .csv, .json, .html, .pdf), AI-synthesized memories, notes, decisions, tasks, reminders, chat messages with the assistant, research queries and reports, and activity events.
AI provider configuration — if you connect your own OpenAI-compatible provider, its endpoint, model name and API key are stored encrypted with AES-256-GCM; the key is never displayed again after saving.
Billing state — payments are processed by Paddle (our merchant of record). We store only subscription status, plan/entitlement flags and customer/subscription ids returned by Paddle. Card numbers never touch our servers.
Technical logs — standard server request logs (time, IP, route, status) used for security, rate limiting and abuse prevention.

3. The Chrome extension reads a page only when you ask

The extension requests the activeTab permission: page content is extracted only when you click “Capture this page” in the side panel, and only for that tab. ContextScribe does not read pages in the background, does not monitor your browsing history, does not record keystrokes, and has no access to any site until you explicitly capture from it. The extracted title, URL and visible text are sent to your workspace, where they appear for your review before being saved as a source.

4. AI processing and recipients

To produce memories, summaries, answers with citations and research reports, your captured content is processed by a large language model. By default this is the platform AI backend configured by the operator; if you connect your own provider in Settings, processing goes directly to that provider using your own API key.
Content is sent to the AI provider only to fulfill your request (capture analysis, chat, research). It is not used to train models, is not shared with advertisers, and is never sold.
Complete list of recipients: (a) the hosting provider that runs the Service, (b) the AI provider that processes your requests — the operator-configured platform backend or your own configured provider, (c) Paddle for billing. No other third parties receive your data. The Service embeds no advertising or analytics trackers.

5. Purposes and legal bases

Providing the Service (contract): storing and processing your account, content, AI synthesis, exports.
Billing (contract): subscription management with Paddle.
Security and abuse prevention (legitimate interest): hashed passwords and sessions, rate limiting, logs.

6. Storage, retention, deletion

Your data is stored in the operator’s production database. In transit everything is served over HTTPS. Passwords are scrypt-hashed, session tokens SHA-256-hashed, and provider API keys AES-256-GCM-encrypted at rest.
We keep your data as long as your account exists. You can delete any individual item (project, source, memory, note, task, reminder, chat, research run) directly in the app at any time.
Full account deletion: Settings → Account → Delete account permanently removes the account and every owned row (projects, sources, memories and their version history, decisions, tasks, chats, research, activity, providers, subscriptions, sessions) in one cascade. Deletion requires typing your account email as confirmation.
Portability before leaving: Settings → Data exports your entire workspace (JSON backup, Markdown and PDF reports) so you can take everything with you.

7. Your rights

Depending on your jurisdiction you may have rights to access, correct, export or erase your personal data, and to object to or restrict certain processing. Most of these are self-service in the app (edit memories, delete items, export backups, delete account); for anything else, contact us and we will act on valid requests within applicable legal timelines.

8. Sharing with other users

Nothing is shared with anyone by default. If you explicitly generate a project share code and hand it to another user, they can read a snapshot of that project and import a copy into their own workspace. Share codes can be revoked at any time and revoked codes stop working immediately.

9. Children

The Service is not directed to children under 13 (or the equivalent minimum age in your jurisdiction) and we do not knowingly collect their personal data. If you believe a child uses the Service, contact us so we can remove the account.

10. International transfers

Your data is processed by our hosting and AI providers, which may operate in countries other than yours. Where required, transfers rely on appropriate safeguards such as standard contractual clauses.

11. Changes to this policy

If we change this policy we will update the “Effective date” above and, for material changes, notify you inside the app before they take effect.

12. Contact

Privacy questions, data requests or complaints: reach us at rafirahman3648@gmail.com — we answer support mail within three business days. If we cannot resolve your concern, you may escalate to your local data protection authority.