Features
Unified API for 24+ frontier and open-weights models
CLI agent with plan-execute-deploy flow
Multi-agent orchestration for parallel coding tasks
Orchestrator-executor agent pattern (June 2026)
End-to-end encrypted inference with customer-managed keys
Zero data retention policy
Automated code refactoring and migration generation
Automated test generation with coverage targets
One-click deployment to staging with health checks
Automated code review with security scanning
Canary release and rollback support
Voice agent support in Pro and above
App builder for visual development
Remote agent for data analysis
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
