Features
Ticket-driven automation: create a ticket, AI agent executes workflow
Multi-agent orchestration: supports Claude Code, Codex, Gemini CLI
Kanban board for drag-and-drop ticket management with real-time status
Skill System: live-editable reusable packages with files and instructions
Full SDLC coverage: design, develop, test, deploy, operate
Self-hosted: Go single binary, open source
Multi-agent coding across multiple AI models
Human-in-the-loop review via pull requests
Traceability: every step tracked from ticket to deployment
Backlog management with AI agent assignment
CI/CD integration via GitHub Actions
Security auditing capabilities
Issue-driven orchestration: agents claim work and execute
Real-time board updates: drag tickets between columns
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
