The tools you use every day. Chat with AI, browse the web, write code, design interfaces, run notebooks, and manage tasks — all in one workspace with shared context.
Dashboard with activity feed, system status, and quick-launch tiles. Your starting point after login.
Conversational AI with any provider. SSE streaming, syntax-highlighted code blocks, tool call indicators. The primary interface for agent interaction.
Integrated code environment. Write, edit, and run code with the agent's assistance. Syntax highlighting, multi-file support, and direct agent access to the same files.
File browser with syntax highlighting, directory tree navigation, and file operations. The agent can read and write to the same file system.
Visual design surface with the Canvas/Slab/Block composition model. Drag blocks, arrange layouts, and build apps from prompts. The agent can create and modify canvas content.
Computational notebooks with code cells, live output, and markdown. Data exploration, prototyping, and documentation in one surface.
Built-in web browser with server-side proxy at /api/browse. The agent can navigate, read page content, take screenshots, and extract data from any website.
Kanban-style task management. Create, organize, and track work items. Drag cards between columns. The agent can create and update tasks.
Architecture visualization. See system components, their relationships, and data flows as an interactive diagram.
Agent memory browser. See what the agent remembers across sessions — project context, user preferences, and learned patterns.
Schedule agent tasks to run on a recurring basis. Cron-style scheduling for automated workflows, reports, and maintenance.
Prompt-driven SVG wallpaper generator. Describe a visual theme and the agent generates a workspace background.
Provider selection, API key configuration, theme preferences, and workspace settings.
Shared knowledge base for your workspace. Documents, references, and context the agent can draw on across conversations.
Browse and manage available tools, skills, and MCP servers the agent can use. See what capabilities are loaded and their permission status.