plugin
AI6 Agent Operating Layer
AI6 Agent Operating Layer is the controlled layer around agents that manages profiles, skills, scheduled work, hooks, sidecars, execution runs, and proof.
Who it is for
Enterprises building agent workflows that need approval, rollback, visibility, and proof.
Problem it solves
It prevents unmanaged agents, invisible scheduled work, and unsafe tool installation.
Activation model
Assisted setup with risk policy and approval gates.
Proof and source paths
- Agent routes exist under /api/agent
- Types and persistence exist
- Enterprise/user guide docs exist
Repo evidence
app/api/agentlib/agent-operating-layerdocs/AI6_AGENT_OPERATING_LAYER_ENTERPRISE_SPEC.md
Capabilities
skill lifecycle
pluginPropose, approve, install, and rollback agent skills.
Runtime registry status
Primary registry
hybrid
Status
partial public mcp
Install gate
Assisted only until agent profile, skill lifecycle, cron, hook, rollback, and proof-ledger tools are exposed through one registry with smoke evidence.
Callable tools
stackfast.dispatch.createstackfast.dispatch.claimstackfast.dispatch.statusstackfast.dispatch.closestackfast.project.news
Missing or gated tools
stackfast.agent.profile.resolvestackfast.agent.skill.installstackfast.agent.cron.schedulestackfast.agent.hook.register
- Storefront product is catalog-ready, not install-ready.
- Current callable surface is the MCP communication/control-plane subset, not the full AI6 operating layer.
Agent-readable queries
enterprise agent operating layerAI agent skills hooks cron approval systemcontrolled AI agent workflows