Introducing RAT: Retrieval Argument Thinking. Extract just the reasoning process from deepSeek-r1 and send it to any LLM via . Boost the second LLM's performance and gain access to missing capabilities like function calling and JSON mode. 👇

🐀🐀🐀

You can install RAT as a command-line tool, allowing you to run it from anywhere by simply typing `rat`. There is also a specialized implementation designed for Claude models that leverages Anthropic's message prefilling capabilities. This version makes Claude believe the reasoning process is its own internal thought process, leading to more coherent and contextually aware responses.

AI-first pull request reviewer with context-aware feedback, line-by-line code suggestions, and real-time chat.

I meant Augmented lol 🤦‍♂️

@OpenRouterAI Shouldn't it be TAG - thinking augmented generation?

@OpenRouterAI @lateinteraction I cannot not think of DSPy when I see this, lol. It feels like pure gold.

@OpenRouterAI We’re so early that we can just make things up

@OpenRouterAI This is just so good. Get the smart ai do the thinking and “less smart” do the job.

@OpenRouterAI Great! Have been waiting to see this since franken-sonnet introduction of yours lol. It is a freaking good idea. And keeping even only "original" thought token is a really powerful boost. Will try to introduce more proper CoT synthesis + instruction set to Claude as prefill..

@OpenRouterAI nice!!! i like the name !

@OpenRouterAI Ufff. That last paragraph said it all. Tks