Features
Multi-executor routing (Copilot, Codex, Claude, Gemini, OpenCode)
Weighted distribution with automatic failover and cooldown
Smart PR lifecycle: create, monitor CI, rebase, merge
Self-healing recovery: autofix, circuit breakers, stale claim reclamation
Flexible task boards: GitHub Issues, Projects v2, Jira, internal board
Telegram control center: 30+ commands, inline keyboards, live digest, Mini App
Multi-agent coordination: shared state, atomic claims, heartbeat liveness
Container isolation: Docker, Podman, Apple Container sandboxes
Fleet coordination: presence tracking, session management, workspace registry
Decisioned PR gates: multi-step merge strategy with CI + review checks
Autonomous planning loop: task decomposition, executor-aware routing
Interactive CLI shell mode and Sentinel watchdog companion
Web Mini App with 7 tabs: Dashboard, Tasks, Agents, Infra, Control, Logs, Settings
WhatsApp notification channel (optional)
Setup wizard with recommended and advanced modes
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
