I applied Lyapunov stability theory to detect when LLM agents spiral

Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness

An open-source cost controller for AI agent loops — stops a loop when it's actually converged and rolls back before it degrades, instead of running to a fixed max_iterations cap. Real-time loop-gain (Aβ) bands + best-so-far rollback. Adapters for LangGraph, CrewAI, AutoGen, LangChain, OpenAI Agents, and Claude Agent SDK; raw API for custom stacks.

TPS-inspired ANDON safety hooks for LLM coding agents — stop defects, learn from failures, improve continuously