Features
Auto-collect data from Slack, Teams, GitHub
Generate 5-layer Persona (values, communication, decision logic, domain expertise, work habits)
Create Work Skill encoding task-specific know-how
Continuous evolution as new data streams in
Export Skill for AgentSkills-compatible agents (Hermes, Claude Code, OpenClaw, Codex)
No manual prompt engineering required
One-click deploy via MyClaw managed hosting
24/7 uptime for hosted agents
Daily backups and encrypted storage
Priority support on Pro, Max, Ultra plans
Access from email, Telegram, WhatsApp, browser
Integrates with Claude Code, OpenClaw, Hermes Agent, Codex
Always-on agent runs on schedule (daily reports, monitoring)
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
