budget-enforcement

Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agents swarms overnight and get your time back.

Self-hosted LLM gateway that routes requests across AI providers (OpenAI, Anthropic, Gemini, Mistral, Ollama) using intelligent multi-policy scoring — including an LLM-native routing policy. Drop-in compatible: just swap the base URL. No database required, built-in cost tracking, budget enforcement and multi-tenant isolation.

Budget enforcement + observability plugin for Hermes Agent. Stops runaway costs before they happen.

Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.

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

Know what your agents cost. Real-time cost tracking, budget enforcement, and financial observability for AI agents. Zero code changes.

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

Streaming metering engine for LLM token billing | Real-time budget enforcement | Built with Flink

Enforcement gateway for AI agents. Nullrun official Python SDK.

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

UnitCause is a real-time cost governance platform for AI agents. It provides budget enforcement, loop detection, cost analytics, and policy management via a web dashboard, REST API, and Python SDK. Set budgets, stop runaway agents, and monitor spending with ease.

A reliability proxy for LLM and agent traffic: guardrails that block unsafe actions before they execute, auto-pause for runaway loops, upstream-failure visibility, and per-agent budget enforcement across providers. Self-hosted, MIT licensed.

Documentation source for nullrun.io — concepts, how-to guides, and API reference for the NullRun agent enforcement platform.

Runnable examples for the NullRun Python SDK

Flight recorder for tool-calling LLM agents. Every step captured in an append-only, hash-chained JSONL trace: tamper-evident, deterministically replayable (50/50 byte-identical), diffable to the first divergent step, budget-enforced (steps, tokens, cost, wall clock). Offline, no API keys, 94% coverage.

Example showing how to enforce LLM budgets on LangGraph agents using the shekel Python library

Hard money-budget enforcement for Slurm jobs — reserves projected cost at submission, rejects unfundable jobs, settles actual runtime, refunds the rest. Hierarchical accounts, banked burst, multi-source funding.

Before/after examples comparing LLM usage with and without shekel budget enforcement

Spec-driven multi-agent orchestration with verification and budget enforcement. Your taste is the product.

A fuse for LLM spend. Four conventional enforcement patterns fail open at 95-100% over ceiling; this holds all four.