Deep Agents Harness Optimized Link

togethercompute · x · 2026-07-15

This is a supplementary entry to the LangChain Deep Agents cookbook, focusing on the Deep Agents Harness optimization for NVIDIA Nemotron 3 Ultra.

Building on the previous post, this example demonstrates how to use the file system as memory during multi-turn agent execution and achieve Ralph loops by refreshing the context in each iteration.

Related event: NVIDIA and LangChain Release Deep Agents Ralph Loop Cookbook(2 posts)→

Original post →

More from coding & agent

coding & agent channel →