Features
Native TUI for terminal use
Multi-session support with parallel agents
Model-agnostic: supports Claude, GPT, Gemini, local models
LSP enabled for automatic language server loading
GitHub Copilot login support
ChatGPT Plus/Pro login support
75+ LLM providers via Models.dev
Desktop app (beta) for macOS, Windows, Linux
Session snapshots and revert controls
Yolo mode for auto-approve permissions
SDK for custom integrations
Privacy-first: no code or context data stored
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
