Features
261 open-source skills for coding agents
64 agents and 84 commands for orchestration
102 security rules via AgentShield
AgentShield session scanning for config vulnerabilities
Cross-harness support for Claude Code, Codex, Cursor, OpenCode
GitHub App for repo-native automation and PR scanning
/ecc-tools analyze command for pattern inspection
ECC 2.0 control plane with session visibility and token optimization
Orchestrator family (orch-*)
Session adapters and MCP inventory
Worktree-lifecycle service
Continuous learning system with instinct-based behavior
Install profiles: core, developer, security, full
Local-first control plane for observability
Community Discord for support
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
