Features
Multi-model chat (GPT-5.5, Opus 4.8, Gemini 3.1 Pro, Sonnet 5, Grok 4.3, Kimi 2.7, etc.)
AI Agent for complex multi-step tasks with auto-approve mode
Parallelized multi-agent research and analysis
Code review and automated PR fixes
Build full-stack web apps with no code, including Stripe integration
AI Desktop IDE with coworking and mode 2 CLI
Automated PowerPoint generation with deep research
AI-powered equity research and portfolio optimization
LinkedIn outreach automation
Data analysis and revenue analytics from Excel
AI audio ad generation with voices and music
Smart document assistant for Q&A (RAG chatbots)
Marketing video generation with AI presenters
Mobile game and app creation without coding
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
