Grok Build vs. Claude Code: I tested which one has the better memory
On September 16, xAI announced memory in Grok Build, its terminal coding agent. The pitch was that Grok “keeps notes The post Grok Build vs. Claude Code: I tested which one has the better memory appeared first on The New Stack .
On September 16, xAI unveiled memory functionality in Grok Build, a coding assistant tool. The feature allows Grok to "keep notes on the conventions, decisions, and project facts that come up" and "later sessions read those notes before touching related code." These notes are stored as Markdown files in both project-specific and global scopes.
Grok Build 1.0.40 utilizes Grok 4.6 through xAI's API key, while Claude Code 2.1.226 employs Opus 5 on the user's subscription. Both tools ran on the same Mac, testing four small Node.js repositories. Each test session consisted of two parts, with each tool instructed to perform a task in one session and then asked to complete a related task in the second session without referring to the initial instructions.
Written by urgent.news from The New Stack's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
