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.
redis golang postgres rate-limiting self-hosted gemini openai finops byok anthropic semantic-cache cost-tracking llm-cost llm-gateway token-budget ai-cost-management spend-limits llm-cost-control openai-budget
-
Updated
Aug 10, 2026 - Go