Cost Control Python Packages

inferrail

Self-hosted OpenAI/Anthropic-compatible gateway: give each AI agent run a dollar budget, enforced before the provider, with a payload-free per-run cost record.

agentguard47

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

kazenai

Runtime budget enforcement and execution telemetry for OpenAI and Anthropic clients.

agent-tokenops

Run-aware token governance for multi-agent systems.

agentic-llm-router

Small cost-aware LLM router for role-tiered OpenAI-compatible and Yandex calls with per-call usage logging.

veronica-core

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

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.

llm-cheap-filter

Deterministic prefilter and cheap-to-chief escalation pipeline for reducing expensive LLM calls in agentic workflows.

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.

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.

opshield

AI agent safety platform: rollback, cost control, circuit breakers, tracing, compliance, and chaos testing. Zero dependencies.

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.

langchain-runcycles

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

llm-token-guard

Track LLM token usage, enforce rate limit & budget policies, and trigger alerts across OpenAI, Groq, OpenRouter, and AWS Bedrock.

bq-readonly-mcp

Read-only BigQuery MCP server for Claude, Cursor, Windsurf, Copilot and other MCP clients. Auto-LIMIT, dry-run cost guard, Application Default Credentials. Run with uvx.

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.

figuard

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

podtrack

Ownership-aware RunPod pod registry and autonomous reaper for shared accounts

flyto-pro-core

Validate agent workflows and check cost and token budgets before execution.

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

runcycles

Python SDK for Cycles — reserve, commit, release budget and risk for AI agents

runcycles-openai-agents

Budget governance for OpenAI Agents SDK — enforce cost limits before tools execute

hengroute

OpenAI 兼容的 AI 大模型网关：一个 API Key 调用所有大模型，智能路由降本，实时可观测，故障自动降级。

hengroute-cli

OpenAI 兼容的 AI 大模型网关：一个 API Key 调用所有大模型，智能路由降本，实时可观测，故障自动降级。