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 @@
+"""Vendored ALFWorld environment runtime.
+
+Minimal subset of SkillRL's agent_system package needed to run
+ALFWorld environments with ReflACT. Original source:
+https://github.com/NTU-LANTERN/SkillRL (Apache-2.0 License)
+"""
+from .alfworld_envs import AlfworldEnvs, build_alfworld_envs
+from .alfworld_projection import alfworld_projection
+from .env_manager import AlfWorldEnvironmentManager