Features
Sandboxes: lightweight ephemeral environments on Kubernetes
Jobs: scalable test execution for Playwright, Cypress, custom suites
Plans: composable validation logic with http-req, run-test, custom actions
MCP server integration for AI coding agents (Cursor, Claude Code, VS Code)
Local development environment with remote dependency connection
Preview environments for every code change without full duplication
Smart Tests: AI-driven regression detection for PR validation
Shift-left automated testing with Playwright, Cypress per PR
Agentic development sandboxes for coding agents
CI-ready test execution with auto-routing to sandboxes
Kubernetes-native, runs inside existing cluster
Shared baseline cluster with up to 100 parallel sandboxes
signadot-validate skill for Claude Code to self-validate changes
AI-powered contract testing
Multi-cluster RouteGroup support (Enterprise)
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
