SkillOpt v0.1.0: initial release

- Skill optimization framework with training loop analogy - 11 benchmarks, 4 model backends (Azure OpenAI, Claude, Codex, Qwen) - WebUI for browser-based training control - Pluggable architecture for extending benchmarks and backends
2026-05-21 17:22:04 +00:00
commit 244e346b83
237 changed files with 30248 additions and 0 deletions
@@ -0,0 +1,9 @@
+"""ReflACT Engine -- the training runner.
+
+Analogous to the Runner in mmengine: orchestrates the full training pipeline
+including rollout, gradient computation, aggregation, optimization, and
+evaluation.
+"""
+from skillopt.engine.trainer import ReflACTTrainer  # noqa: F401
+
+__all__ = ["ReflACTTrainer"]