SaneBox

Automatically categorizes incoming emails into user-defined buckets (newsletters, promotions, social, updates, etc.) using machine learning models trained on user behavior patterns and email metadata. The system learns from user actions (opens, clicks, deletions) to continuously refine classification accuracy without requiring manual rule configuration. Integrates directly with IMAP and Exchange Web Services protocols to intercept and classify messages at the server level before they reach the inbox.

Detects unsubscribe links in newsletter and promotional emails, then provides one-click unsubscription functionality through the SaneBox interface without requiring users to navigate to external unsubscribe pages. The system parses email headers (List-Unsubscribe, List-Unsubscribe-Post) and email body content to locate unsubscribe mechanisms, then executes the unsubscription request via HTTP or email protocols. Maintains a log of unsubscription attempts and handles bounce-back scenarios where unsubscribe links fail.

Allows users to set up email forwarding rules (forward emails matching certain criteria to another address) or delegate email management to team members through the SaneBox interface. Forwarding rules are applied server-side via IMAP or EWS, ensuring emails are forwarded even if SaneBox is not running. The system maintains audit logs of all forwarding actions, showing which emails were forwarded, to whom, and when. Delegation allows team members to access and manage emails on behalf of the primary account holder with granular permission controls.

Assigns numerical priority scores to incoming emails based on sender reputation, historical interaction patterns, content relevance, and contextual signals (e.g., emails from frequent contacts, emails mentioning your name, time-sensitive keywords). The scoring engine runs on email metadata and content at delivery time, then surfaces high-priority emails prominently in the SaneBox interface while deprioritizing low-engagement senders. Uses collaborative filtering to identify patterns across similar user cohorts to improve scoring accuracy.

Provides native bidirectional synchronization with IMAP-compatible email servers and Microsoft Exchange Web Services (EWS) through protocol-level integration that reads email metadata, headers, and content directly from the mail server. The integration layer handles authentication (OAuth2, basic auth, app-specific passwords), maintains persistent connections or polling intervals to detect new messages, and executes server-side operations (folder creation, message moves, flag updates) via IMAP commands or EWS API calls. Supports multiple simultaneous email accounts and handles protocol-specific edge cases (e.g., Gmail's IMAP label mapping, Exchange's calendar/contact folder structures).

Enables users to select multiple emails and execute batch operations (move to folder, delete, mark as read, apply labels) through the SaneBox interface, with changes synchronized back to the email server via IMAP or EWS. The system queues bulk actions, executes them asynchronously to avoid blocking the UI, and maintains a transaction log that allows users to undo recent bulk operations within a configurable time window (typically 24-48 hours). Handles partial failures gracefully — if some emails fail to move, the system reports which emails succeeded and which failed, allowing users to retry failed operations.

Provides full-text search across email content, headers, and metadata with support for natural language queries (e.g., 'emails from John about the Q4 budget') that are parsed into structured search filters. The search engine indexes email content locally or via the email server's search capabilities, then returns ranked results based on relevance scoring. Supports advanced filters (date range, sender domain, attachment presence, read/unread status) that can be combined with natural language queries to narrow results.

Allows users to create, store, and reuse email templates and canned responses within the SaneBox interface, with support for variable substitution (sender name, date, custom fields) and quick insertion into reply/compose windows. Templates are stored in SaneBox's database and can be organized by category (customer service, sales follow-up, etc.). When composing a reply, users can search for and insert templates, with variables automatically populated from email context (sender name, email subject).

Maintains bidirectional synchronization of email read/unread status between the SaneBox interface and the email server via IMAP or EWS protocols. When a user marks an email as read in SaneBox, the change is immediately reflected in the email server and vice versa. The system handles edge cases such as marking multiple emails as read in bulk, handling conflicts when the same email is marked read in multiple clients simultaneously, and preserving read status across email client switches.

Allows users to create, rename, and organize email folders/labels within the SaneBox interface with support for nested hierarchies (e.g., Projects/Q4/Budget). Changes are synchronized back to the email server via IMAP or EWS, creating corresponding folder structures on the server. The system handles provider-specific folder naming conventions (Gmail's label system vs. IMAP's folder hierarchy) and provides drag-and-drop UI for reorganizing folder structures.

Automatically detects emails with attachments and provides quick access to attachment metadata (filename, size, type) and download functionality through the SaneBox interface. The system can filter emails by attachment presence, search for emails containing specific file types (PDFs, images, documents), and provide bulk download or organization options. Attachment metadata is indexed to enable fast retrieval without downloading the full attachment content.