neurogenesis__register_compute_profile
Register a compute execution profile to define model type, quality, costs, latency, and resource requirements for routing tasks across local and cloud compute.
Instructions
[neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Wu Wei compute routing (NG7): register an execution profile — {id, kind?, quality_score [0,1], cost_per_1k_input_tokens?, cost_per_1k_output_tokens?, latency_ms?, gpu_memory_gb?, max_context_tokens?, local?}. A profile can be a local model, cloud API, rules engine, or cached workflow. Profiles are yours — routing never invents capacity.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| profile | Yes |