Meta adds customizable "spaces" to Muse AI assistant
Users can now create app-like experiences within Muse, such as shopping hubs or school dashboards, and integrate third-party apps like Gmail and Notion.
1 source · cross-referenced
- Meta’s Muse AI assistant now supports customizable "spaces" that function as app-like experiences within the app.
- Users can create spaces for specific needs, such as shopping, school, music tracking, or trivia games.
- Spaces can integrate with third-party apps like Gmail, Google Calendar, OpenTable, and Notion to pull and update real-time information.
- New "Active Memory" and "Active Focus" features from the Muse Wonder AI model are being added to Muse and Meta AI chatbot.
- The rollout is available to all Muse users, with future plans to enable sharing and collaboration on spaces.
Meta’s Muse AI assistant now allows users to create customizable "spaces"—app-like experiences within the Muse app tailored to specific needs. These spaces can function as shopping hubs, school dashboards, music trackers, trivia games, and more.
Users can generate a new space by describing it, and Muse will create it. The assistant can integrate with third-party apps such as Gmail, Google Calendar, OpenTable, and Notion to continuously pull and update information like pricing, dates, and other details in the background.
Interactivity within spaces includes checking off tasks, adding notes, and making edits. Users can also adjust the placement of spaces in the Muse app, such as keeping them in the sidebar, moving them to the main tab, or scheduling their visibility—for example, swapping a weekly planner for weekend plans on Saturdays.
Meta is also introducing "Active Memory" and "Active Focus" capabilities from its Muse Wonder AI model into the Muse app and Meta AI chatbot. These features aim to improve the assistant’s ability to recall relevant past information during conversations and work toward user-defined goals.
The rollout of spaces is available to all Muse users. Meta is also exploring ways to enable users to share their spaces with others and collaborate on them.
- Nov 11, 2026 · Hugging Face
Hugging Face proposes token pooling-aware training to improve compressed multi-vector retrieval
Trust79 - Nov 11, 2026 · TechCrunch — AI
Fractile raises $720M Series C to develop AI chips and compiler stack
Trust79 - Nov 11, 2026 · The Verge — AI
Google’s Tabletop AI experiment lets users build custom collaborative apps via waitlist
Trust79