Portkey-AI/gateway ? reverse-engineered prompt

Build me a fast AI gateway that sits in front of different model providers and gives me one simple OpenAI style API to use across them. I want to be able to point it at a local server, send chat requests through it, and have it route to different LLMs like OpenAI, Anthropic, Bedrock, and others without changing my app code.

It should include a nice web console where I can see requests and logs, plus basic config options for retries, fallbacks, load balancing, and simple guardrails like blocking certain words or unsafe outputs. Make it easy to run locally with one command, and also support Docker or other common deployment options. If anything in the docs is unclear, look up the current docs online and follow the project’s existing behavior as closely as possible.