Files
openclaw/docs/cli/agent.md
T
Tabula Myriad a9ae1a6778 feat: Triad development iteration complete
Matrix Protocol:
- docker-compose.matrix.yml: Dendrite homeserver + PostgreSQL + Nginx TLS
- src/channels/plugins/matrix-channel.ts: OpenClaw plugin implementation
- docs/matrix-triad-setup.md: Setup guide with auth scheme (@tm1-4:triad.local)

MCP Server Integration:
- docs/mcp-triad-integration.md: SearXNG, Playwright, GitHub MCP configs
- docs/mcp-curiosity-mapping.md: Gap-to-capability mapping

Node Sync Architecture:
- src/services/node-sync-service.ts: WebSocket peer sync + presence detection
- src/services/node-sync-service.test.ts: Unit tests
- docs/node-sync-architecture.md: Architecture docs

Triad Resilience:
- scripts/triad-corruption-check.mjs: SQLite + log + config + git integrity
- docs/triad-resilience.md: Recovery procedures
- .secure/deployment-logs/README.md: Schema v2
- skills/triad-heartbeat/SKILL.md: Corruption check integration

NPM Publish Workflow:
- scripts/npm-publish.mjs: version, changelog, validate, publish, rollback
- .github/workflows/npm-publish.yml: GitHub Actions with provenance
- docs/npm-publish-guide.md: Complete documentation

All deliverables tested in Docker before production.
2026-03-24 00:44:50 -04:00

1.1 KiB
Executable File

summary, read_when, title
summary read_when title
CLI reference for `openclaw agent` (send one agent turn via the Gateway)
You want to run one agent turn from scripts (optionally deliver reply)
agent

openclaw agent

Run an agent turn via the Gateway (use --local for embedded). Use --agent <id> to target a configured agent directly.

Related:

Examples

openclaw agent --to +15555550123 --message "status update" --deliver
openclaw agent --agent ops --message "Summarize logs"
openclaw agent --session-id 1234 --message "Summarize inbox" --thinking medium
openclaw agent --agent ops --message "Generate report" --deliver --reply-channel slack --reply-to "#reports"

Notes

  • When this command triggers models.json regeneration, SecretRef-managed provider credentials are persisted as non-secret markers (for example env var names, secretref-env:ENV_VAR_NAME, or secretref-managed), not resolved secret plaintext.
  • Marker writes are source-authoritative: OpenClaw persists markers from the active source config snapshot, not from resolved runtime secret values.