A structured, persistent reasoning workspace for AI. 20 tools for thought chains, branching, revision, search, tagging, and SQLite session persistence that survives context window resets and server restarts.
Enables agents to navigate users through pre-defined decision trees by submitting answer labels, returning deterministic next instructions without extra LLM calls. Supports domain-independent procedural workflows with state tracking, handling of unknown responses, and a read-only Web UI.
12 deterministic graph-theory tools for structural analysis. Describe systems in EN syntax (subject do: action needs: inputs yields: outputs) — get topology, bottlenecks, blast radius, critical paths and lot more. No AI inside the computation.
Local memory for coding agents that can refuse, not only recall. A rule carrying a machine-checkable proof blocks the matching command before it runs, while prose-only rules can warn but never block.
Enables AI clients and agents to turn a new idea into a structured set of clarifying questions, technology options, upward design breakdowns, reverse reasoning, and risk assessments so users can steer top-level design decisions. It also supports saving insights and building a bidirectional design tree of concepts and their implementations.