Cost Control Python Packages

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.

figuard

Pre-flight spend authorization for AI agents. Reserve-confirm lifecycle, concurrency-safe, append-only audit ledger.

veronica-core

Runtime containment kernel for LLM agents. Enforces budget, step, retry, and circuit-breaker limits before the model call.

agentguard47

Your AI agent just burned $200. AgentGuard stops it at $5. Runtime cost guardrails for AI agents — budget enforcement, loop detection, kill switch. Zero dependencies, MIT licensed.

agentmesh-proxy

The governance plane for AI agents — policy, budget, and audit across every framework. Istio for AI agents.

state-harness

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

agentbrake-sdk

The emergency brake for multi-agent systems. Stop runaway LangChain & CrewAI agents before they burn your budget.

shekel

LLM budget control and cost governance for AI agents. Python library for token budgets, usage limits and guardrails for OpenAI, Anthropic, LangChain, LangGraph and agentic systems.

langchain-runcycles

LangChain agent middleware for Cycles — pre-tool-call authorization and per-tenant budget enforcement for Python agents using create_agent

monetise-circuit-breaker

Runtime economic governance for AI agents. Circuit Breaker adds risk-managed execution, cost ceilings, and kill switches to autonomous AI workflows.

figuard-langchain

Pre-flight spend authorization for AI agents. Reserve-confirm lifecycle, concurrency-safe, append-only audit ledger.

runcycles

Python AI agent budget control — enforce LLM cost limits, tool permissions, and multi-tenant policies before agent actions execute.

agentcap-guard

Provider-agnostic hard dollar budgets + loop detection for AI agent runs. Stops the spend before it happens.

tenet-python

Python SDK for Tenet — a hard cost cap, approval gates, and a tamper-evident audit log for every AI agent tool call. One line wraps any agent framework.

costcutter

CostCutter is a serverless, Python-based tool that helps users manage AWS resources and avoid surprise cloud costs. By monitoring budgets and automatically cleaning up resources when thresholds are exceeded, CostCutter keeps your AWS environment tidy and cost‑efficient.

runcycles-openai-agents

Runtime budget, action, and audit authority for the OpenAI Agents SDK — enforce LLM cost limits, tool call caps, and audit trails before execution.

enzu

Budgeted LLM runs with hard caps + typed outcomes + async job mode. Python/CLI/HTTP. OpenAI-compatible.

magicrails

🛑 Emergency brake for AI agents. Hard budget caps, loop detection, and state-stasis guards in 3 lines of Python. Stops runaway agents before the $500 overnight invoice.

veloryn

Deterministic cost-bounded execution for multi-step LLM workflows

langchain-kavachos

The kill-switch between your AI agents and your credit card. Agentic spend governance for Claude Code, OpenAI Codex, and any JSONL-logging agent.

crewai-kavachos

KavachOS DAN gate + budget guard for CrewAI agents — pre-execution governance via AEGIS

xshieldai-langchain

The kill-switch between your AI agents and your credit card. Agentic spend governance for Claude Code, OpenAI Codex, and any JSONL-logging agent.

xshieldai-crewai

The kill-switch between your AI agents and your credit card. Agentic spend governance for Claude Code, OpenAI Codex, and any JSONL-logging agent.

tokvigil

Application-layer AI usage control platform with SDKs and a policy engine to enforce budgets, limits, and audit logs per user, feature, and plan.