# Claude Memory

Hacker Approved page: https://hackerapproved.com/p/claude-memory-feature/

5 people recommended Claude Memory in Hacker News comments, 1 had mixed feelings and 18 criticized it, November 2025 to October 2026. It was recommended in 3 of 12 months, in 5 threads. It does not meet the Hacker Approved badge rule.

**Verdict:** Criticized more than recommended: critics say it often pulls in obsolete or unrelated memories and can derail current tasks; those who recommend it cite remembering recurring details such as project plans and personal facts.

Summary written by Claude from the comments below.

## What people warn about

- Memories are verbose and low value (3 comments in the sample): "All the memories Claude created for me fell in the category remember-to-not-forget, so I disabled it altogether." ([source](https://news.ycombinator.com/item?id=47900050)) "I found Opus's 4.8 memories largely lacking value." ([source](https://news.ycombinator.com/item?id=48847968)) "the way it writes them is really annoying" ([source](https://news.ycombinator.com/item?id=49876616))
- Pulls in unrelated or obsolete memories (3 comments in the sample): "It inevitably ends up dragging in things that are unrelated and unimportant to the current task." ([source](https://news.ycombinator.com/item?id=49052988)) "much more often harmful, pulling in obsolete info that muddies the waters about current tasks" ([source](https://news.ycombinator.com/item?id=48777419)) "I didn’t want fragments of old conversations haunting new ones" ([source](https://news.ycombinator.com/item?id=46259957))
- Poorly matches memories to context (2 comments in the sample): "The amount of times I want to discuss an approach for it to pull memory out and have that steer the decision making is so…" ([source](https://news.ycombinator.com/item?id=49729954)) "terrible at contextualizing memory access and makes huge leaps that don’t make sense" ([source](https://news.ycombinator.com/item?id=49052987))
- Opaque storage and hard to control (1 comment in the sample): "Those auto memories are also annoying because by default they are not version controlled and land in a secret location." ([source](https://news.ycombinator.com/item?id=49056465))

## Other chatbot features people recommend

- [Claude Artifacts](https://hackerapproved.com/p/claude-artifacts/): 17 recommend, 8 mixed, 9 criticize
- [ChatGPT Health](https://hackerapproved.com/p/chatgpt-health/): 11 recommend, 9 mixed, 68 criticize
- [Gemini Gems](https://hackerapproved.com/p/gemini-gems/): 6 recommend, 2 mixed, 4 criticize

## Where to get it

- [Visit the official site](https://claude.ai/login)

## The badge

A product earns the Hacker Approved badge when at least 10 people recommend it, recommenders outnumber critics at least 2 to 1 (mixed feelings count toward neither side), it was recommended in at least 4 of the 12 months and in at least 5 different threads, and no single thread supplies more than half of the people who recommend it. Health and money products are never badged.

## Cite as

Hacker Approved, "Claude Memory", https://hackerapproved.com/p/claude-memory-feature/ (5 recommend, 1 mixed, 18 criticize; Hacker News comments, November 2025 to October 2026).

Counts updated 2 Nov 2026, with data through October 31, 2026.