DTS

MCTS-inspired parallel beam search for conversation optimization. Explore multiple dialogue strategies simultaneously, stress-test against diverse user personas, score with multi-judge consensus, and discover winning conversation paths that single-shot LLMs miss. Maintained by MVPandey on GitHub, where it has earned 36 stars from the community.

It's actively developed around ai-agents, asyncio, beam-search, and is a solid reference for anyone building with these tools.