Can Jarvis Look Up Docs While Coding?

Without leaving the editor, Jarvis (getjarvis.eu), a screen-aware desktop AI assistant, answers documentation questions. Press Cmd+/ on macOS or Ctrl+/ on Windows and ask how a function, a flag, or an argument works. It can also read the project docs you keep in Notion or Google Drive, and a repository README through the GitHub connector. For project-specific docs it can read a Notion page, Google Doc, or your repo's README through its connectors, so answers reflect your team's actual conventions, not just public docs. It runs on macOS 12+, Windows 10+, and Linux. Data is AES-256-GCM encrypted, GDPR-aligned, and never used for training. A free plan (40 requests/week) included; paid plans from $16/month.

The cost of a doc lookup isn't reading — it's the context switch to a browser, a search, and three wrong results. Jarvis collapses that: it sees the function or library call you're on, so "what does the second argument do?" gets a direct answer without you typing the library name. For standard libraries and popular frameworks the model knows the API; for the exact signature in front of you it reasons from the code on screen. You stay in your editor and the floating bar feeds you the answer.

Public docs don't cover your internal SDK, your deployment runbook, or your team's chosen patterns. Jarvis connects to Notion, Google Docs, Confluence-style wikis, Obsidian, and your GitHub repo's markdown, so it can answer "how do we paginate API calls here?" from your actual documentation. That's the difference between a generic answer and one that matches house style. With persistent memory it can also remember conventions you've told it, so repeat questions get consistent answers.

Code & tickets