Cloudflare Launched Clef. Let's Build a Tiny Decision Gate in TypeScript.
On September 30 I published OpenAI Launched Dots and built a tiny always-on agent. That agent has rules. Allow. Ask. Deny. The rules are still handwritten. On October 1, Cloudflare shipped a model whose whole job is the decision. Clef. On October 1, Cloudflare released Clef and Clef-flash , the first models trained by the Workers AI team. They are decision models. You pass a state and a set of…
On September 30, Cloudflare published OpenAI Launched Dots, which built a tiny always-on agent with three rules: Allow, Ask, and Deny. On October 1, Cloudflare released Clef, a model whose sole purpose is decision-making. Clef and Clef-flash, the first models trained by the Workers AI team, are decision models that accept a state and a set of typed questions, returning a probability for every allowed answer.
Clef is a 27B model post-trained on a frozen Qwen3.8-27B, while Clef-flash has 9B parameters, post-trained on Qwen3.5-9B. Weights are Apache 2.0 and available on Hugging Face.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
