Features
Persistent cloud desktop running 24/7
Built-in AI agent integrated at OS level
Full Linux filesystem accessible by agent
Dock, windows, desktop icons – familiar UI
Built-in terminal, code editor, and browser
Agent runs terminal commands and browses web
Individual private desktops
Team shared desktops with user isolation
Access from any device via browser
Agent memory and files stored on container filesystem
Laguna XS.2 model (33B params, 3B active, on-device)
Laguna M.1 model (225B params, 23B active, via API)
256K context length for multi-step reasoning
Multi-agent orchestration with planning and tool use
Sandboxed agent execution environments
Developer surfaces: agents, TUI, IDE extensions, binaries
Custom foundation models deployed on-prem or in VPC
Data connectors to repos, databases, data warehouses
Role-based access control for humans and agents
Executive-grade governance and auditability
On-prem, VPC, and workstation deployment (defense only)
Forward Deployed Research Engineers embed with teams
Real-time observability with end-to-end traces
Air-gapped network support
Open-weight model weights available
