Drop-in LLM proxy that cuts AI API costs 30-40% with semantic caching, cost-aware routing and multi-provider failover.

1 stars 0 forks 1 watchers TypeScript MIT License
ai-gateway anthropic claude cost-optimization gpt llm llm-proxy llmops nextjs openai semantic-cache token-optimization typescript
1 Open Issue Need Help Last updated: Jul 28, 2026

Open Issues Need Help

View All on GitHub

Drop-in LLM proxy that cuts AI API costs 30-40% with semantic caching, cost-aware routing and multi-provider failover.

TypeScript
#ai-gateway#anthropic#claude#cost-optimization#gpt#llm#llm-proxy#llmops#nextjs#openai#semantic-cache#token-optimization#typescript