Features
Multi-agent orchestration (Orchestrators, Task Owners, Workers)
Parallel execution for research, implementation, and QA
Human-reviewable pull requests with isolated changes
Terminal-native CLI with local-to-remote execution
Cloud collaboration across engineers, PMs, and stakeholders
Memory and context management across sessions
Planning and reasoning for complex refactors
Browser automation (Instant Sites)
LSP manager for code intelligence
MCP (Model Context Protocol) support for external tool access
Background tasks and session history
Agent commits with provider authentication (GitHub)
Skills, plugins, and hooks customization
Lumen Scout, Outpost, Frontier model family
Enterprise deployment: public cloud, managed single-tenant, fully air-gapped
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
