Features
Multi-agent workspace with role-based specialists (Partner, Engineer, Product Lead, Designer)
Parallel agent collaboration with handoffs
Per-agent persistent skills and memory on disk (plain files)
Mixed model assignment per role (Claude Opus, GPT-5.5, Gemini, etc.)
Background Partner agent for knowledge mining and upgrade proposals
Local-first: everything runs on your machine, no cloud dependency
Supports 11+ CLI agent runtimes (Claude Code, Codex, Gemini CLI, Cursor Agent, etc.)
Task-level context with project workspaces
Live streaming of agent actions and file edits
Run statistics: elapsed time, tokens, tool calls, lines changed
Agent handover with one-line briefs
Custom crew composition and agent creation
Plain-file storage for skills and memory (version-controllable)
Open-source codebase on GitHub (MIT license)
Mobile companion app with end-to-end encrypted pairing
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
