AI HOT (Curated Pool)Aug 26, 2026, 02:02 UTC+8

Claude's memory works everywhere, and you decide what's in it

Claude 记忆功能全面打通聊天与 Cowork，用户可逐条查看和编辑

Anthropic extended Claude's memory beyond chat to Claude Cowork and Claude Code. Users can now view, edit, or delete individual memory entries in a unified panel. The post doesn't specify memory capacity limits or cross-session latency, but confirms memory works across products and users can disable it entirely.

Why it matters: Anthropic extended memory from chat to Cowork and Code, with cross-product sharing and per-item user control — a real UX upgrade for heavy Claude users. Score held at 78 because the post doesn't disclose capacity limits or cross-session latency, leaving key details missing.

Read the original ↗Export Markdown

Take

The reason this is worth a look: Anthropic turned memory into a cross-product feature instead of a chat-only toggle. You get a unified panel where you can see, edit, or delete individual entries Claude has stored, plus a global off switch. Compared to ChatGPT's implicit, hard-to-audit memory, this is a lot more transparent for regular users.

Two things the post doesn't cover: what's the memory cap, and does cross-session retrieval add latency? If Claude Code has to pull a batch of memories every time it starts up, that could get annoying. Also, sharing memory between Cowork and Code means your coding preferences might bleed into collaborative docs—whether that's helpful or noise depends on the workflow.

I'd read this as a controllability update, not a memory capability leap. The real signal to watch is whether enterprise teams start routing internal knowledge management through Claude because of this.

Source: AI HOT (Curated Pool) · claude.com
Published: Aug 26, 2026, 02:02 UTC+8 · Aug 26, 2026