cost-control

An open-source Python tool that controls AI agent loops using real-time convergence signals instead of a fixed max-iterations cap, with rollback and adapters for popular agent frameworks.

LLMCap is a proxy for LLM API calls that hard-stops requests when a dollar cap is reached, with support for major providers and companion tools for VS Code, CLI, and Windows.

tokentoll is a GitHub Action and CLI that scans Python and JavaScript/TypeScript code for LLM API calls, estimates spend, and blocks pull requests when cost or model-policy thresholds are exceeded.

Millwright is a self-hosted Rust LLM router that sits between apps and model providers to enforce policy-based routing, control spend, and preserve provider/model affinity for cache reuse.

Kotro is a local control plane for coding agents that governs MCP tool actions and LLM traffic with one binary. The page shows install options, supported clients, dashboard access, and concrete controls like schema pinning, redaction, cache, budget, and circuit breaker behavior.

Self-hosted LLM gateway for cost-aware model routing, spend tracking, and policy-based traffic control across multiple providers.

A long-form technical article on building ship-ready AI agents in Rails with the Anthropic Ruby SDK, covering tool design, agent loops, MCP servers, human approval, testing, and cost control.