Hello World! 👋 Project Ember is a compositional framework for compound AI systems. It gives ML researchers a toolset to achieve comparable performance to frontier LLMs at 1/1000th the cost (or less) with inference-time scaling. github.com/PyEmber/ember

Ember: an inference-time scaling architecture framework 🧵 (1/8)

So we just OSS’ed this Ember library, and called it an inference-time scaling architectures framework. We deliberately avoided calling it an agentic or multi-agent framework. Here's why, via a quick thread 🧵 (1/6)

One of the underrated strengths of this framework is its suitability for production deployment—offering both reliability and reduced hallucinations. This work builds on concepts from the SPECIFICATIONS paper (arxiv.org/abs/2412.05299), with the Ember Operator abstraction at its

🔥 Workshop by Jared Quincy Davis at the Agentic AI Summit (Aug. 2) highlighting how ML researchers are using Ember to 10x price performance for agentic systems 🧠 Thanks UC Berkeley RDI for hosting a great event!