OpenClaw configuration templates for different LLM providers and models.
All tenant VMs auto-connect to the AgentCore Gateway and gain these MCP tools.
Tool definitions live in deploy/lambda/agentcore_tools/ + deploy/stack.py.
agentcore.enabled: true in config.yml and redeploy.
Groups bundle skills together so a tenant can subscribe via group: "team-sre"
instead of listing every skill. A tenant's effective skill set =
tenant.skills ∪ group.skills. Tenants without scoping fields get every skill (legacy broadcast).
Skills are shared across all tenants. They're plain markdown files in
s3://${ASSETS_BUCKET}/skills/<name>/SKILL.md and are synced to every host
every 5 minutes via cron, then injected into VMs at launch.
Click a row to view / edit. Use Groups (above) to scope skills to specific tenants.
s3://${ASSETS_BUCKET}/skills/<name>/ directly).
metrics.enabled: true in config.yml and redeploy.
The stack will provision Amazon Managed Prometheus + Grafana, and ADOT collectors on each
host start scraping in ~3 minutes after rollout.
Each host's host-agent exposes these gauges on
:8899/metrics. ADOT scrapes every 30s and remote-writes
to AMP via SigV4 (no static credentials).
| Metric | Type | Labels | Description |
|---|---|---|---|
openclaw_vm_health | gauge (0/1) | tenant | 1 if VM responded to ping, else 0 |
openclaw_vm_cpu_pct | gauge | tenant | Per-VM CPU usage (percent of allocated vcpus) |
openclaw_vm_memory_used_mb | gauge | tenant | Per-VM memory in active use (MB, from VmRSS) |
openclaw_vm_memory_balloon_mib | gauge | tenant | Balloon size held by the host (MiB) |
openclaw_vm_disk_used_mb | gauge | tenant | Per-VM data disk used (MB) |
openclaw_vm_disk_total_mb | gauge | tenant | Per-VM data disk capacity (MB) |
openclaw_vm_disk_used_pct | gauge | tenant | Per-VM data disk used (percent) |
Copy into Grafana → Explore → AMP datasource.
sum by (tenant) (openclaw_vm_memory_used_mb)
min_over_time(openclaw_vm_health[1m]) == 0
openclaw_vm_disk_used_pct > 90
| Tenant | Source Status | Backup Time | Size | Actions |
|---|---|---|---|---|
| ↳ previous backup | ||||
Backups are retained for 7 days (S3 lifecycle). Orphan backups are from tenants that have been deleted — restoring creates a new tenant with the backup's data volume.
Optional features and their current status. Toggle in config.yml and re-run ./setup.sh.
Allocatable resources = physical × ratio. Tune in config.yml under host:.
Live distribution of registered hosts and their tenants across Availability Zones.
Set multi_az.enabled: true in config.yml to spread the ASG.
| Availability Zone | Hosts | VMs | vCPU used / total |
|---|---|---|---|