Features
Open-source TypeScript framework
Memory with persistent context
RAG (Retrieval Augmented Generation) with knowledge bases
Guardrails for safe AI interactions
Tools (function calling) API
MCP (Model Context Protocol) support
Workflow chain API (andAll, andAgent)
Supervisor agent orchestration (subAgents)
Middleware for intercepting agent I/O (sanitize, validate, retry)
Tool routing for scaling tool use without prompt stuffing
Resumable streams for long conversations
VoltOps console: observability, tracing, monitoring
Actions & triggers for automated workflows
Evals (evaluations) for agent performance
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
