Meta launches Spaces to organize Muse agent tasks into project-specific workspaces
Spaces lets users create dedicated tabs for tasks like vacation planning or gift tracking, with background updates from connected apps.
1 source · cross-referenced
- Meta’s Muse agents gain Spaces, a sidebar feature to organize tasks into project-specific workspaces.
- Users can create a Space for a vacation plan, gift tracker, or DIY project, with Muse updating info from connected apps.
- Meta says Spaces are built automatically when users describe an idea in chat.
- Muse Voice, a video chat feature for agents, was announced the day before Spaces.
Meta’s Muse agents now support Spaces, a feature that organizes agent-assisted tasks into dedicated, project-specific workspaces within the same interface. These Spaces appear in a sidebar and can be opened as tabs for focused work, such as planning a vacation, tracking holiday gifts, organizing a wedding, or managing DIY projects.
Meta describes Spaces as ‘custom experiences’ that can be created by describing an idea in chat; the agent then builds the corresponding Space, whether a tracker, planner, or project board.
Spaces can integrate with third-party apps and services, with Meta stating that connected apps keep Spaces updated in the background. For example, new concert dates, price changes, or savings progress are reflected automatically without user prompts.
Meta also announced Muse Voice on the day before Spaces, enabling users to video chat with their Muse agent and issue verbal commands. This follows the recent launch of Muse agents, which Meta says reached 10 million users in the U.S. and Canada less than two months after debuting.
- Nov 11, 2026 · Latent Space — swyx
OpenAI demonstrates voice steering, cloud handoffs, and personal agents for Codex at AI Engineer Code Summit
Trust79 - Nov 11, 2026 · The Verge — AI
OpenAI to launch verified AI Business Agents in ChatGPT for US e-commerce and service businesses
Trust79 - Nov 10, 2026 · Latent Space — swyx
NaiveAI releases Naive-N0.5-Flash coding model with ultrafast token throughput
Trust74