Features
Prompt management with versioning
Evals platform with LLM-as-Judge and automated eval builder
Synthetic data generation (filter, label, generate)
Fine-tuning support (distill into smaller models)
RAG (index, chunk, retrieve, rerank, semantic chunking)
Agents with sub-agents, skills, tools, and MCP support
Auto-Optimizer that tunes prompts to eval scores
AI Assistant for guided experimentation and optimization
Git-backed dataset and eval versioning
Structured output (JSON) and reasoning support
Human ratings and golden datasets
Collaboration through reviews, issues, and team feedback
190+ supported models (cloud and local)
Open-source Python library for production deployment
Source-available desktop app
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
