Features
Spec-driven development: define features as living specs
Multi-agent orchestration with coordinator agent
Built-in browser panel for autonomous E2E testing
Bring your own agent: Claude Code, Codex, OpenCode
Assign different models to different sub-agents
MCP (Model Context Protocol) server support
Git integration with isolated worktrees per feature
Real-time agent activity streaming
Side-by-side diffs before committing
Shared notes and spec with every change
Customizable UI with split views
Isolated workspaces with terminal and code editor
Figma sync (via MCP or manual)
Agent workflow chaining with retry and fallback
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
