A truth maintenance system for AI coding agents — one graph over code, intent, plan, and the why: every belief justified, anchored to the code it concerns, and flagged when it stops holding. pip install yigraf
Verified knowledge for AI agents. Compress context, extract and store facts, define rules, and ask questions — get deterministic answers with proof, not LLM guesses. Connect agents via MCP, Python SDK, TypeSc
Commitment tracking for LLM agents — a normative overlay that gives long-running agents a scoreboard of their own commitments, not just a memory of what happened.
A logic-based Truth Maintenance System (LTMS) and pattern-directed reasoning engine in pure Python, after Forbus & de Kleer's Building Problem Solvers. Docs: https://pisanuw.github.io/ltms/
