Taskuary

Taskuary is a personal AI work manager for people whose requests arrive across email, chat and ticket systems. It gathers those requests into tasks and lets AI agents prepare the work for your review.

• Inbox and task triage: Bring Outlook, Gmail, Teams, Slack and issue trackers such as Jira and GitHub into one list, with thread context and tasks grouped by what needs attention.
• Agent work and approval: Delegate tasks to Claude Code, Codex or Gemini, watch their progress, and review or edit prepared replies before anything goes out.
• Reports and daily briefings: Request recurring reports in plain language and see a morning overview of changes, meetings and pending work.
• Memory and shared context: Taskuary learns from corrections and edits, while agents share discoveries and handoff notes; you can review or delete learned preferences and disable learning.

Taskuary is free, open source under the MIT license, and runs on Windows, macOS and Linux, or on a self-hosted server with Docker. It requires no Taskuary account and stores its data locally. Ollama supports local models, so AI prompts can stay on your machine; hosted AI providers and coding CLIs receive the context needed for delegated work. Taskuary removes recognizable credentials from outgoing prompts, but that filtering doesn't catch every secret written in ordinary language. The project is early in development, and breaking changes remain possible.