Features
Automatic integration test generation
Self-healing test maintenance (retires stale tests, adds new)
Baseline capture and diff detection for API behavior
Blast radius analysis via SCIP dependency graph
Local environment orchestration with Docker
Mock external dependencies (real DBs, queues, caches)
MCP integration for AI agents (Cursor, Claude Code, Windsurf)
CLI and IDE plugin support
Real-time audit reports inside IDE
Validation of APIs, workflows, contracts, error handling, auth, edge cases
Supports TypeScript, Python, JavaScript
Token consumption reduction (88%+ via KIT index)
Zero code retention (runs locally, code never leaves machine)
SOC 2 Type II compliance (in progress)
Git-based project required
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
