Find a Past or Upcoming Meeting With AI.

Ask in plain language and Jarvis (getjarvis.eu), a desktop AI assistant, searches connected Google Calendar or Outlook. Connect a calendar over OAuth, press Cmd+/ on Mac or Ctrl+/ on Windows, and ask when you last met someone or which events touched a topic. Answers come back in the floating bar without opening the calendar app. Jarvis searches your calendar through the connector API and ranks results semantically. Routing goes to a frontier model for accuracy. Persistent memory remembers attendee aliases (Maria = Maria Garcia) across sessions. OAuth tokens use AES-256-GCM and EU data residency for GDPR compliance. Free tier handles daily searches; Pro at $16/month and Unlimited at $32/month raise quotas. Works on Mac, Windows, and Linux. Same flow works for Apple Calendar (native), Microsoft Teams meetings, Zoom history, and any calendar accessible via the connectors.

Google Calendar's native search matches event titles and descriptions but stumbles on natural-language questions. Ask "find every meeting about the EU launch" and native search returns nothing if no event title literally said "EU launch" — even if you had three meetings about it called "Sprint 23 planning". Semantic AI search reads the event titles, descriptions, attendee lists, and (with permission) attached docs to find meetings about the topic regardless of how the event was named. Jarvis pulls candidate events through Calendar's API for the date range you specify, fetches the descriptions and any linked documents (if Drive is connected), and routes the relevance scoring to a frontier model. Results include the meeting title, date, attendees, and a one-line summary of why it matched.

Install Jarvis (Mac, Windows, Linux). Sign in. In Settings → Integrations connect Google Calendar (OAuth), Outlook (Microsoft 365 OAuth), or Apple Calendar (native macOS). Press Cmd+/ on Mac or Ctrl+/ on Windows. Type a natural-language search: "when did I last meet with Maria Garcia?", "find every meeting about the EU launch in the last 60 days", "meetings I have next week with the design team", "show me every 1:1 I had with my CEO this year". Jarvis returns matches in 5-15 seconds with date, attendees, and a one-line excerpt. To go deeper: "summarize the most recent of these", "draft a follow-up email to attendees of the last one", "prep me for the next one in the list". Cross-connector queries also work: "find every meeting where we discussed the contract Alex sent in Gmail" pulls from both Calendar and Gmail.

Meetings