Features
Detects performance regressions (e.g., render loops)
Catches state & effect anti-patterns (missing deps, mutable dependencies)
Architecture issue detection (prop drilling, no-derived-state)
Inline PR comments with explanations and fix suggestions
Blocks PRs on regressions via required status checks
Cooperative scanning with time budgets
Health score for React codebases
Autofix capability for certain rules
Respects .gitignore and reads ESLint/oxlint config
Standalone oxlint and ESLint plugins
CI setup command (react-doctor ci)
Works with React, Next.js, Vite, TanStack, React Native, Expo
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