Succeeded in ATAlem Tuzlak
feat(ai, ai-persistence): subagent results, run context, limits, keys, and follow-up calls (#1723)
main1d0f8f1Open on GitHubResource usage
Average and peak CPU and memory per agent, against its launch template's capacity.
By launch template
- avg
- avg → peak
- over capacity
- capacity
| Launch template | Agents | CPU (avg / peak) | Memory (avg / peak) |
|---|---|---|---|
| linux-medium-js4 vCPU 4 GB | 51 over capacity | 144.69% / 312.8% of 400% | 1.87 GB / 5.2 GB (over capacity) of 4 GB |
Agents
| Agent | CPU (avg / peak) | Memory (avg / peak) | Details |
|---|---|---|---|
| Agent 0linux-medium-js4 vCPU 4 GB | 156.73% / 293.5% | 2.14 GB / 5.2 GB (over capacity) |
See per-agent resource charts
This run didn't use Nx Agents. Enable Nx Agents to see per-agent CPU and memory for your CI runs.