Budget Control Python Packages

kazenai-finops

Python SDK for pre-call AI budget controls and customer-, feature-, and workflow-level cost attribution.

langchain-runcycles

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

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

onceonly-sdk

Execution safety & governance layer for AI agents: idempotency, budgets, tool control, audit logs.

agenthalt

Production-grade guardrails for AI agent function calls. Budget, scope, rate-limit, PII & deletion guards with Human-in-the-Loop approval.

reliapi-sdk

Beta self-hosted HTTP and LLM proxy with Redis-backed caching, non-streaming LLM idempotency, and budget guardrails.

thinkbudget

Adaptive inference budget controller - caps how much your LLM thinks per query, tracks GPU cost in real-time.