msgvault¶
Archive a lifetime of email and chat. Fast keyword search, opt-in semantic search, and local AI workflows.
Supports Gmail, Google Calendar, Microsoft Teams, Granola, Circleback, Beeper Desktop, IMAP, and Microsoft 365 mail sync; verifiable backup snapshots; PST, MBOX, and Apple Mail import; and chat/text import from WhatsApp, iMessage, Google Voice, Facebook Messenger, and SMS Backup & Restore.
Read the Introduction to learn more about why this project was created.
Install¶
Windows (PowerShell):
Then set up OAuth credentials and start syncing. You can also build from source.
New in 0.18.0
Archive Beeper Desktop chats and Granola or Circleback meeting notes; browse meetings in the TUI; install bundled agent skills; retrieve attachments by hash through the HTTP API; and use native Windows ARM64 releases. See the Changelog for the full release notes.
Why msgvault?¶
Your email and message data is yours. msgvault downloads a complete local copy of your email (from Gmail, IMAP, or local archives) and imports chats and texts from WhatsApp, iMessage, Google Voice, Facebook Messenger, and SMS Backup & Restore, and can sync Beeper chats plus Granola and Circleback meeting notes. Keyword search, analytics, the TUI, and the MCP server query your archive. Source services are contacted only by authorization/registration, sync, media-backfill, and deletion workflows that you run or schedule explicitly. Optional vector search calls only the embedding endpoint you configure; use a local or self-hosted endpoint if message text must never leave your machine or network.
Years of PDFs, photos, documents, and spreadsheets buried in your inbox become deduplicated content-addressed objects that can be searched and exported by hash. Your data is no longer locked behind a provider's web interface or API; it lives in an archive on disk that you own and control.
Features¶
Full Email Backup
Downloads complete messages from Gmail or any IMAP server, including raw MIME, labels, metadata, and every attachment. Every PDF, photo, spreadsheet, and document you've ever received or sent is extracted and stored locally, deduplicated by content hash.
Calendar Sync
Archive Google Calendar alongside email. Events — including organizers, attendees, recurring series, and cancellations — become searchable by keyword and by meaning, and their participants dedupe with your email contacts. Read-only and incremental.
Teams Sync
Archive Microsoft Teams chats, channels, replies, link attachments, and inline media through delegated Microsoft Graph. Teams records use message_type = teams so they can be searched and queried separately from email.
Meetings & Beeper
Sync Granola and Circleback notes and transcripts into a dedicated TUI browser, and archive chats and media from networks bridged through Beeper Desktop. Search each source separately by message type.
Backup Snapshots
Create incremental, append-only backup repositories for the SQLite archive and attachments. Verify snapshots byte-for-byte, restore into a fresh archive home, and sync the repository off-site with ordinary file tools.
Lightning-Fast TUI
Explore hundreds of thousands of messages with instant aggregation and drill-down. Powered by DuckDB over Parquet, hundreds of times faster than SQL JOINs, in a small footprint.
Full-Text Search
SQLite FTS5-powered search with Gmail-like query syntax. Search by sender, date, label, size, attachments, and more.
Semantic & Hybrid Search
Opt-in semantic search with vectors stored locally, plus hybrid ranking that fuses BM25 and vector similarity via Reciprocal Rank Fusion. Point msgvault at a local or self-hosted OpenAI-compatible embedding endpoint and query by meaning, not just keywords. Exposed through local CLI search, the HTTP API, and MCP server.
Multi-Account
Archive multiple sources in a single database, group accounts into collections, manage per-account identities, and deduplicate safely.
Incremental Sync
Uses Gmail History API for efficient updates after initial full sync. Resumable checkpoints for interrupted syncs.
MCP Server
Expose your archive to AI assistants through the Model Context Protocol. Search metadata or bodies lexically, run semantic search, and find matches within one message.
Agent Skills
Install bundled read-only skills that teach Claude Code and Codex how to search the archive, retrieve attachments, and run analytics from the terminal.
Web Server
REST API for programmatic access to your archive. Optional cron-based background sync scheduling. Build dashboards, automations, and integrations.
Local Import
Import PST archives, MBOX archives, Apple Mail .emlx exports, and chats/texts from WhatsApp, iMessage, Google Voice, Facebook Messenger, and SMS Backup & Restore. Messages are indexed and searchable alongside your email data.
Safe Deletion
Stage messages for deletion in the TUI or via AI assistant, review manifests, then permanently delete from Gmail or IMAP provider.
How It Works¶
