Entities
Entities are structured context blobs the agent reads before acting. They are version-controlled, project-scoped, and managed with veirox entity.
The 13 entity kinds
Rules, skills, and commands can also be set platform-wide by a platform admin — visible read-only in every project alongside your own.
| Kind | When to use |
|---|---|
memory | Durable facts the agent writes and reads across sessions — services, people, recurring incidents. |
knowledge | Long-lived reference docs: architecture, team conventions, how-tos. |
skill | Reusable capability doc — describe how to do a task once, reused across sessions. Can be platform-wide. |
command | Custom slash command, invoked with /name in chat. Can be platform-wide. |
rule | Always-on or path-scoped guardrail injected into the agent's prompt. Can be platform-wide. |
hook | Pre/post-tool-use policy hook (YAML) — allow, deny, or enrich a tool call. |
runbook | Step-by-step operational procedures the agent follows when triggered. |
issue | Tracked problem — status, priority, assignee. |
incident | Active operational incident — severity, status, linked sessions. |
postmortem | Incident retrospective, linked back to the incident. |
finding | Security or quality finding — severity, status, source, CVE refs. |
story | Jira-style unit of work — acceptance criteria, Definition of Done. |
plan | The agent's ordered, status-tracked execution plan for a story. |
CRUD operations
veirox entity create --kind runbook --title "Deploy checklist" --body-file ./deploy.md veirox entity list --kind runbook veirox entity get --kind runbook --ref deploy-checklist veirox entity update --kind runbook --ref deploy-checklist --body-file ./deploy-v2.md veirox entity delete --kind runbook --ref deploy-checklist
Versioning
Every update increments the version counter. Pass --version <n> for optimistic concurrency — the backend rejects the update if your base version is stale.