Features
Codebase Q&A agent for querying large repos
Automated root cause analysis with Trace
PR review automation (41% faster cycles)
Custom agent builder (Forge) for workflows
Pre-built Specialists for debugging, testing, planning
Codebase knowledge graph for contextual understanding
Sandboxed execution environment for agents
Multi-LLM support (multiple model backends)
Compliance and security features for regulated industries
Open-source core with enterprise deployment options
SWE-bench Lite 63% accuracy
Integration with Slack, GitHub, Notion
Spec-driven development workflows
Error analysis and troubleshooting via stack traces
Full-stack implementation from feature descriptions
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
