849 B
849 B
Design goals
Primary goals
-
Deterministic governance
- enforce policy outside model weights
- deterministic decisions for authority, budgeting, and audit
-
Capability-based execution
- no ambient permissions for models or tools
- explicit, revocable capabilities with TTL and scope
-
Cognitive resources as first-class
- context budgets, compute budgets, risk budgets
- cost-aware scheduling (latency vs confidence)
-
Provenance
- structured event model for “what happened and why”
- support tamper-evident logging (later)
-
Isolation domains
- strong sandboxing for tools and untrusted workers
- fault containment and graceful degradation
Non-goals (for v0.x)
- kernel-resident LLM inference
- universal scheduler for all workloads
- solving “alignment” in the model