Features
Nexus governance layer with configurable risk posture
Supervised (approve per proposal) and fully autonomous modes
Autonomous bug detection and fix PRs
Security vulnerability scanning and auto-fix
Automated test coverage for uncovered code paths
Code quality improvements (tech debt, dead code, performance)
Feature development from tickets
Continuous scanning even when queue is empty
Proposal submission and approval workflow
Unlimited projects and seats on all plans
Monthly compute budget with granular tracking
30 to 365-day retention depending on plan
Integrations with up to unlimited third-party tools
Custom Docker support on Team and Scale plans
Open-sourced Nexus judgment layer
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
