Provides recursive language model capabilities to AI assistants, enabling efficient exploration of large contexts through iterative Python code execution.
Socratic AI that turns vague problems into structured intent specs — objective, outcomes, edge cases, constraints. Zero-config locally, or team mode for evidence, dependency graphs, and governance. Ships 7 auto-triggering Claude Code skills. Build the right thing.
Implements the Tree of Thoughts framework for structured reasoning and decision tree exploration, enabling LLMs to explore multiple reasoning paths, evaluate them, and backtrack.
Enables users to visualize and interact with Claude's chain-of-thought reasoning from extended thinking traces, turning them into interactive reasoning maps with typed moves, dependency graphs, timelines, and replay mode.