Features
Multi-agent team collaboration demos
Graph workflow examples with routes and loops
Streaming agent examples (Python, Java)
Human input and dynamic workflow patterns
Integration with Gemini, Gemma, Claude, and local models via Ollama/vLLM
MCP and A2A protocol client/server examples
Custom function tool demonstrations
Skill and artifact management samples
Session and memory state handling
Evaluation and observability setup examples
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
