Self-hosted spend firewall and gateway for LLM ( OpenAI / Anthropic / Gemini ). Hard per-user & per-project budget caps that block runaway costs before the API call, plus cost-per-customer tracking, semantic caching, and failover. One line of code, single Go binary.

Security proxy for AI agents (OpenClaw, LangChain, CrewAI). Protects API keys, enforces spend limits, blocks dangerous endpoints. Local-first Rust binary — your credentials never leave your machine.

The governance layer LLM proxies promised as a TypeScript library you can read. Every call runs through one governed pipeline: rate limit → spend caps (per-user + global circuit breaker) → cache → schema-validated provider failover → usage log → LLM-judge No sidecar proxy to deploy.

A policy engine and safety guardrails for tool-using AI agents — evaluate every tool call as allow / deny / quarantine with spend limits, allowlists, command-safety, path protection, rate limits, and authority levels.