5 projects
omegaprompt
Provider-neutral prompt calibration engine with sensitivity-ranked meta-axes, hard-gate x soft-score fitness, walk-forward ship gates, guarded/expedition profiles, and explicit capability/risk reporting across Anthropic, OpenAI, Gemini, and local OpenAI-compatible backends. Optional sub-tools (mini-omega-lock, mini-antemortem-cli) distribute separately and plug in via the omegaprompt.preflight interface.
antemortem
CLI for pre-diff risk classification with schema validation and disk-verified citations.
omega-lock
Audit gate for tuned candidates: stress boundaries, hard constraints, walk-forward validation, and append-only trails.
mini-antemortem-cli
Analytical preflight for omegaprompt calibration: deterministic classifier over eleven source-backed calibration trap patterns. Emits AnalyticalFinding records the omegaprompt pipeline consumes via derive_adaptation_plan.
mini-omega-lock
Empirical preflight probes for omegaprompt calibration: judge consistency, endpoint schema reliability, context-budget margin, latency, noise floor. Emits PreflightReport records the omegaprompt pipeline consumes via derive_adaptation_plan.
