Loop Detection Python Packages

agentguard47

Python runtime checks for AI agents: budgets, loops, retries, and local traces. Zero runtime dependencies. MIT.

loopbrake

Brakes for stuck AI agents. Learns how long your agent's tasks normally take, stops the one that runs way past that, and says why. For Claude Code, Codex and your own Python agents. Runs locally, zero dependencies.

octopoda

Persistent Memory Kernel for AI Agents — crash recovery, shared memory, audit trail, real-time dashboard

loopgain

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.

longguard

In-flight circuit breaker & loop recovery for LangGraph, LangChain, OpenAI & Anthropic agents. Catches reasoning loops, prevents runaway LLM costs with budget hard caps, and auto-injects Reflect & Pivot prompts.

mimo-stable

Cross-model LLM degenerate loop detection and engineering guardrails. MiMo is the initial case study; this project does not claim model-level repair.

drift-detector-agent

Behavioral drift detection for LLM agents — catch vocabulary loss, tool changes, loops, and stagnation before they break production.

reivo-guard

Open-source guardrails that auto-kill runaway AI agents — budget enforcement, loop detection, quality verification