CoreProxy AI
Lead
lead
engineer
Overview
CoreProxy AI is a production-ready, high-performance API Gateway and reverse proxy engineered using Fastify (Node.js), Redis, and PostgreSQL. It is specifically designed to secure, cache, and rate-limit internal LLM/AI API endpoints (OpenAI, Gemini, Ollama) for multi-tenant applications.
Key Features:
- Multi-Tenant Auth: Validates custom 'X-CoreProxy-Key' headers against an ultra-fast Redis cache.
- Rolling-Window Rate Limiting: Strict token-bucket restriction handled via Redis based on client tiers (Free, Tier 1, Tier 2).
- Dynamic Reverse Proxying: Dynamically forwards valid requests to target AI endpoints while masking your master API keys.
- Complete Audit Logging: Automatically logs structural metadata to PostgreSQL.
Perfect boilerplate for SaaS founders looking to protect their AI budgets from token abuse and API depletion. Fully containerized.
Mission
CoreProxy AI Business Plan
Value Proposition
CoreProxy AI is a high-performance, multi-tenant API Gateway designed specifically for AI/LLM workloads. It provides a secure, sub-millisecond overhead layer that handles rate-limiting, token-bucket budgeting, and API key masking. This prevents LLM budget abuse and centralizes observability for distributed AI applications.
Target Customer
- Startups & Scaleups: Companies building AI-driven products needing to protect their API budgets.
- Enterprise IT: Organizations centralizing LLM access across multiple teams/departments.