Features
Persistent memory across sessions using markdown files
Append-only daily session logs (notes/)
Mutable knowledge files with last-updated timestamps
Identity configuration via IDENTITY.md
Knowledge index via KNOWLEDGE.md
Works with OpenCode, Claude Code, Codex, Cursor, Windsurf
Git version control for full history and rollback
Multiple agents via separate repos, same kernel
Minimal setup: clone, start agent, talk
Open source with 200+ GitHub stars
No database or external services required
Optional kern-ai runtime for Telegram, Slack, daemon mode
User pairing and backup/restore in kern-ai
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
