Skip to content
PricingFeaturesResources
Open Dashboard

Privacy policy

Effective November 10, 2026

Voruna brings Windows files and connected cloud sources into one search experience, with an optional AI Agent. This policy explains what stays on your PC, what is sent for a feature you choose, and how account and connector data is handled.

On this page

  1. About this policy
  2. What we collect
  3. How we use information
  4. Where processing happens
  5. Google sign-in information
  6. Service providers and sign-in
  7. Cookies and similar storage
  8. Retention and deletion
  9. Security
  10. Your choices
  11. Children
  12. Location and transfers
  13. Changes
  14. Contact

About this policy

This policy describes how the Voruna website and Windows application handle information. Use the public contact form for support or privacy questions, or Your data in account settings to download your data or submit an account request.

What we collect

Account and sign-in details. Email address, optional display name or username, profile picture, appearance preference, account identifier, account creation time, and a salted scrypt password hash for password accounts. We do not store the readable password. If you use Google sign-in, we request only OpenID Connect identity and email; we retain the Google account identifier and verified email to find or create your Voruna account and sign you in. The Google tokens used to complete sign-in are not retained as account credentials, and this sign-in flow does not request access to your Google Drive or other Google content. Google sign-in details are not used for advertising or AI features.

Passkeys. If you register a passkey, we retain its credential identifier, public key, counter, device or transport information, and the name and timestamps used to manage it. Your authenticator retains the private key. Existing password or Google sign-in remains an account recovery option.

Account, billing, and usage records. Plan and subscription status, renewal date, Stripe customer/subscription identifiers, and AI usage totals by billing period. Where prepaid developer billing is enabled, we also record credit purchases, remaining credit, metered API usage, refunds, and adjustments. Verified payment records include Stripe charge identifiers, captured and refunded amounts, currency, and dispute status; public profiles expose only rank, never these amounts or payment identifiers. Stripe processes payment details in its hosted payment flow. Voruna does not receive full card numbers.

AI feature inputs and outputs. When you use an AI feature, the service receives the information needed for that request. This can include submitted text for summarization, a prompt, and file names, paths, and modification details supplied for file assistance. The configured inference services process these requests on the service PC. AI job records retain submitted inputs and generated outputs under the cleanup schedule below.

Local file and media index. File search keeps names, paths, sizes, extensions, and modification times in the desktop app's local index. When you enable visual search, the desktop app sends small image previews and available video poster previews through the website to the AI service PC for embedding. Original image/video files are not uploaded. Preview requests are processed in memory over the private connection and are not saved as AI jobs or queued for later processing. Returned search vectors are cached in an encrypted, account-specific desktop cache, bounded to recent supported media and available cache space. Local service media indexing can also keep image/video metadata and derived vectors. Metadata matching stays on the indexing PC. With automatic indexing enabled, semantic text search also sends bounded excerpts from supported .txt, .md, and .rst files, together with their display titles, through the website to the configured AI service PC. Semantic indexing respects the configured search roots and ignored folders. Derived vectors and bounded text excerpts are stored in an encrypted, account-specific cache on the desktop; changed or removed sources are checked before search results are returned. This semantic processing is separate from metadata-only local search, and the service PC may be a different computer from the desktop. Background indexing runs while the desktop app is running; ignore a folder to stop future file indexing for that location. Original source files remain on the indexing PC.

Local clipboard history. While you are signed in to the Windows app, copied text is kept in an encrypted, account-specific local history for up to 24 hours, subject to storage limits. Text marked by supported password managers or applications as excluded from clipboard history is skipped. Clipboard history and search matches stay on your PC and are not stored in cloud search catalogs. When automatic clipboard translation is enabled, eligible short text is sent to the configured local translation service, with Google Cloud Translation as a fallback if that service is unavailable; Voruna does not retain the translated text. The app skips known sensitive formats and screens for common secrets, but screening may not catch every sensitive item. You can turn off automatic clipboard translation in desktop Settings. Pinning a clipboard item to the shortcut wheel retains a local encrypted copy until you remove it. Opening an item in a text editor creates a temporary local copy.txt file; these exports are cleaned up after 24 hours while the app runs or at its next startup.

Connected providers. If you connect an account, the service stores its provider token encrypted in the PC service database. Available connections are GitHub (repositories, code, issues, pull requests, and optional commit searches; private repositories require your explicit repository permission); Discord (profile and joined servers); Notion (shared pages and permitted blocks); Linear (issues and descriptions); GitLab (authorized API data); Slack (authorized search results); Dropbox (authorized file metadata); and Todoist (tasks and projects). The specific data returned depends on the provider account, permissions you grant, and your saved search preferences. You can restrict supported search categories from the connection's Search preferences. Disabling a category changes Voruna searches; it does not revoke an OAuth permission. Revoke access with the provider or disconnect to remove the stored credential. The website may cache bounded repository metadata and query results in memory for a few minutes, scoped to the connected account and credential. The desktop also stores an encrypted account-specific catalog of connected titles, URLs, and permitted excerpts, and derived search vectors, for up to seven days. Background refreshes update this catalog while the app runs. Successful snapshots replace obsolete entries; disconnecting or changing search permissions invalidates that source on the next account refresh. Web search titles and snippets can be saved in the same catalog. Temporary RPC results may be retained to finish or retry an operation. Disconnecting removes the stored connector credential and attempts to revoke provider access where supported. A failed revocation or a provider without this endpoint can leave the grant active; you can revoke remaining access in provider settings. Disconnecting does not erase data held by the provider.

Agent communication. Telegram, Discord, and email are optional messaging channels, not personal-account search connections. A one-use link code binds a sender to your account. Bot credentials and message bodies are encrypted in the service database; routing identifiers, checkpoints, and task metadata are also stored. Conversations retain at most 50 threads with 80 messages per thread. Disconnecting stops future work through that channel; deleting a conversation removes its saved conversation content. Providers and recipients can retain their own copies. Inbound email is processed by Cloudflare and must pass sender authentication. Revoke custom bot tokens with their provider when needed.

Developer access. API and MCP credentials permit the access shown when they are created; anyone holding one can make those requests. Where end-user delegation is enabled, a signed-in user separately approves the developer credential and permitted connectors. We retain the developer and end-user identifiers, connector permissions, expiration and revocation state, and a hash of the delegation credential. The approved credential is temporarily stored encrypted until the developer retrieves it once, or the consent request expires. The developer can receive permitted search results and content through that delegation, without receiving your stored provider token. Revocation stops subsequent authorized requests; it cannot recall information a client already received. Usage and security records may remain after revocation.

Company workspaces. A company workspace stores its name, membership roles, invitation email addresses and hashed invitation tokens, billing references, and administrative audit events. Owners and admins can see the members and manage invitations. Joining a workspace does not share your files, private connections, prompts, or chat history with other members, and does not change your personal plan or unrelated personal use. Company seats cover the member's use within that company workspace while coverage is active. Organization owners manage company billing; custom-contract details are restricted to authorized administrators. Invitation links expire after seven days unless accepted or revoked earlier. We keep membership, billing, and agreement records as needed to operate the company plan and meet applicable obligations.

Agent tools and communications. Agent can read authorized connected-app data and prepare changes such as sending messages, creating tasks or updating documents. Ask mode is read-only. Work mode can execute authorized tools without an additional in-app approval; Windows elevation and provider permissions still apply. Provider actions that require confirmation are sent after you approve them; single-use, account-bound approvals expire after five minutes. You may authorize Agent to message your own linked Telegram, Discord or email address and to create or change your own automations without approving each such message or schedule update. Scheduled runs use your normal Work Credit allowance. Disconnecting a channel stops future delivery to that channel.

Approved workspace files and browser. The desktop Agent can inspect and edit supported files only in folders you approve. Edits save a local undo record; undo refuses to overwrite changes made afterward. File contents needed for your task may be transmitted to the configured inference provider. Undo records remain on your device. Browser tools act in the embedded browser with session-specific tabs and profiles, subject to the chosen permission mode. Browser content is untrusted input. Local Work mode also provides command and PowerShell execution using your Windows account permissions, which can affect files and applications outside the selected project. Command side effects are not covered by the file-edit undo system. Ask mode does not expose write tools.

Service and request data. The service stores AI job status, submitted input payloads, completed result text, errors, usage and billing records, and security records such as webhook receipts. AI job inputs can remain with the job record until routine cleanup. The website host may also process request and diagnostic metadata, such as IP address, request time, and error information, under its own service terms and privacy notice.

Contact messages. If you use the public contact form, we store your reply email address, the request category, your message, and a request status so we can review and respond. The form is available without an account. For abuse prevention, the service also stores keyed hashes of your email address and network address for rate limiting; it does not store the raw network address in the contact-request record. Contact requests do not expire automatically.

Managed app authorization. Optional Gmail, Google Drive, Google Calendar and Outlook connections use Composio-managed authorization where available. Connecting these apps is separate from signing into Voruna. Composio stores and refreshes the provider credentials and receives app requests, tool arguments and returned data necessary to perform authorized operations. Actual access depends on the permissions granted at the provider. Each connection is tied to its Voruna account, and multiple provider accounts may be linked.

Sessions and browser storage. The website uses an HttpOnly signed session cookie for up to 14 days, a short-lived Google sign-in state cookie, an encrypted Google recovery cookie lasting up to 15 minutes when the account service is unavailable, and a separate cookie for the restricted admin area. The desktop app stores a signed session token for sign-in. Optional MFA stores an encrypted TOTP secret and hashes of recovery codes; successful setup or disabling MFA changes the security version used to revoke existing sessions. Temporary interface state and pending billing/service operations use session storage.

How we use information

  • Create and secure accounts, authenticate sign-ins, and provide the requested desktop and website features.
  • Process the particular text or file metadata you submit to an AI feature and return its result.
  • Apply plan limits, measure usage, manage subscriptions, and address payment issues.
  • Protect the service, prevent abuse and fraud, troubleshoot failures, and comply with legal obligations that apply to the operator.

Where processing happens

The website, account database, background workers and private gateway run on the configured Voruna host PC. Public HTTPS traffic passes through Cloudflare. The website communicates with its account service over an authenticated loopback connection. Local file indexing runs on the device where the desktop app is installed.

Agent inference is routed through the configured model service; Auto first uses Kilo’s free router, then falls back to Logfare and Google Gemini when available. Selecting Gemini or an available free OpenRouter stealth model routes through that provider first; provider failures may fall back to other configured services. Prompts, relevant conversation context, submitted images and selected tool results may be transmitted to that service to generate responses. Local search and local undo records are distinct from this AI processing. The provider’s applicable terms and retention practices govern processing on its systems.

Google sign-in information

Google sign-in supplies identity information to create or access your Voruna account. It does not itself grant access to Gmail, Drive or Calendar. Separate app authorization is required for those services. Authorized Google app data may be processed by Composio to execute requested tools and, when relevant to your Agent task, by the configured inference provider. We do not sell Google user data or use it for advertising.

Voruna does not sell Google identity information, share it with advertisers, or use it to train generalized AI models. Identity information is used for sign-in and account security. Our use and transfer of Google API data follows the Google API Services User Data Policy, including its Limited Use requirements.

Service providers and sign-in

  • Cloudflare provides the website's public network and security connection and may process request and network metadata under its own policies.
  • Stripe hosts checkout and subscription management and processes payment details. Voruna receives subscription and customer identifiers and payment status, not full card numbers.
  • Google and Microsoft provide optional app authorization. Google also provides optional account sign-in. Connected-app access is limited to the permissions you approve.
  • Composio manages optional connected-app authorization, stores and refreshes those provider credentials, and executes authorized app tools.
  • Kilo, Logfare, Google Gemini, OpenRouter and their selected inference providers process the prompts, relevant conversation context, attachments and tool results supplied to Agent.
  • Telegram, Discord, Cloudflare Email Routing and the configured email-delivery provider handle messages sent or received through the channels you link, including channel identifiers, sender and recipient addresses, message contents and delivery metadata.
  • Email delivery uses Resend or a configured SMTP provider for account correspondence and linked Agent replies. The provider receives recipient addresses, message contents and necessary delivery metadata.
  • Contact handling stores messages in the Voruna service database so we can review them and respond manually using the reply address you provide. The form does not send an automatic email response.

Connector access is limited to supported providers and approved permissions. Google sign-in information is used for authentication and account security, and is not used for advertising or to train generalized AI models. Google account permissions can be reviewed and revoked in Google Account settings.

Cookies and similar storage

Cookies support sign-in, the short-lived Google sign-in flow, restricted admin access, theme preferences and your analytics choice. With permission, we collect aggregate public-page views, selected link clicks, broad device and referral categories, stored on our service PC for up to 90 days with cleanup on a later event. A randomly generated browser identifier rotates on the next visit each UTC day, and the server retains only a one-way daily hash to estimate unique browsers. The daily hashes follow the same 90-day retention as the counts. Rejecting analytics removes the identifier from browser storage. We do not include search queries, account IDs, full referrer URLs or IP addresses in analytics records. You can change your choice through cookie preferences. We do not add advertising pixels or third-party analytics scripts.

Retention and deletion

The PC service is configured to remove completed, failed, and cancelled AI job records once they are more than 90 days old. This is routine cleanup and only runs when the service's pruning task runs, so removal may occur later. Cleanup removes the job input and result stored in that record. Pending queue messages are configured with a maximum seven-day retention period; actual queue retention depends on the deployed provider configuration. Account, password-hash, billing, usage, and other account-linked records do not have an automated self-service deletion path or a published fixed retention period. You can submit a deletion or correction request from Your data in settings. Requests are recorded for manual review; a submitted request does not immediately change or delete data, and some records may need to be retained for service security, accounting, or legal reasons.

Local indexes and other locally stored app data remain until the user removes them or an available cleanup function removes them. Uninstalling may preserve app data and should not be treated as a complete deletion request.

Security

The implementation uses HTTPS for the website, scrypt password hashing, signed and HttpOnly web sessions, rate limits, encrypted queue payloads, and authenticated private-network service requests. These measures reduce risk but cannot guarantee security. Use a unique password and avoid submitting sensitive information that is not needed for the requested feature.

Your choices

  • View and update the profile fields available in dashboard settings.
  • Sign out of the website or desktop app. You can also remove the website's local/session storage in your browser.
  • Download a JSON copy of available account, usage, AI job, connector-name, and privacy-request submissions/status from Your data in dashboard settings. The file reports if history limits mean some records were not included; use the contact form to ask about those records. The export excludes credentials and internal notes. Local app data stored only on the Windows PC is not included in this website account export.
  • Submit a correction or deletion request from Your data in settings. Requests are tracked for manual review and are not completed automatically.

Children

Voruna is intended for people aged 13 and older. Account setup asks users to confirm they meet this minimum age. The service is not intended for children under 13. A parent or guardian who believes a child under 13 has provided information can submit a message through the contact form.

Location and transfers

Voruna's website functions run in a US region. The PC service runs on the configured PC, and payment, sign-in, networking, and connector providers may process data in the United States or other countries. This means information may be handled outside the country where you live.

Changes

We will update this page when the product or its data practices materially change and revise the effective date. Review the page when you use the service.

Contact

Use the public contact form for questions or privacy concerns. Signed-in users can also use Your data in account settings.

Voruna
PricingPrivacyTermsRefundsCookiesAcceptable useContact
© 2026 Voruna