Claude Memory
Shares rank 4 of 6 chatbot features by recommenders
Recommended for remembering recurring details such as project plans and personal facts. Critics say it often pulls in obsolete or unrelated memories and can derail current tasks.
Recommended for remembering recurring details such as project plans and personal facts. Critics say it often pulls in obsolete or unrelated memories and can derail current tasks.
30 people gave an opinion
- recommend it
- 6
- criticize it
- 24
- approval share
- 20%
Recommended in 4 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- 0.2 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
What people warn about
Each mark is one comment
Memories are verbose and low value
“All the memories Claude created for me fell in the category remember-to-not-forget, so I disabled it altogether.”
Comment from 25 Apr 2026 in “Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do” “Memories are too verbose/specific/yet-generic for the value captured.”
Comment from 9 Jul 2026 in “A new way to reflect on how you use Claude” “I found Opus's 4.8 memories largely lacking value.”
Comment from 9 Jul 2026 in “A new way to reflect on how you use Claude” - Comment from 28 Sep 2026 in “Prompting Claude Opus 5.5”
Pulls in unrelated or obsolete memories
“It inevitably ends up dragging in things that are unrelated and unimportant to the current task.”
Comment from 25 Jul 2026 in “The new rules of context engineering for Claude 5 generation models” “much more often harmful, pulling in obsolete info that muddies the waters about current tasks”
Comment from 3 Jul 2026 in “Claude, please stop trying to memorize random crap” “I didn't want fragments of old conversations haunting new ones”
Comment from 14 Dec 2025 in “Show HN: AMP – open-source memory server for AI agents (MCP, SQLite, D3.js)” Poorly matches memories to context
“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 obnoxious”
Comment from 16 Sep 2026 in “Claude Cowork and chat are now one Claude” “which is terrible at contextualizing memory access and makes huge leaps that don’t make sense”
Comment from 26 Jul 2026 in “The new rules of context engineering for Claude 5 generation models” “terrible at contextualizing memory access and makes huge leaps that don’t make sense”
Comment from 25 Jul 2026 in “The new rules of context engineering for Claude 5 generation models” Opaque storage and hard to control
“Those auto memories are also annoying because by default they are not version controlled and land in a secret location.”
Comment from 26 Jul 2026 in “The new rules of context engineering for Claude 5 generation models” “it's a much more casual and black box experience”
Comment from 6 Mar 2026 in “Show HN: CodeYam Memory – comprehensive memory management for Claude Code”
Other chatbot features people recommend
The four most recommended other chatbot features, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claude Artifacts | 25 | 12 | 68% | 8 | — | Approved |
| ChatGPT Health | 20 | 70 | 22% | 2 | — | — |
| Gemini Gems | 9 | 5 | 64% | 7 | — | — |
| Claude MemoryThis page | 6 | 24 | 20% | 4 | — | — |
| Claude Projects | 6 | 7 | 46% | 4 | — | — |
What people said
27 of the 30 comments that mention it, newest first. Each links to the original comment.
“the way it writes them is really annoying”
“it tends to list dates for significant requests already, so it can untangle this sort of thing”
“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 obnoxious”
“It behaves much better than claude’s automated “memory” system, so I use that”
“literally throwing away all our hard-earned lessons of the last 3 decades”
“Those auto memories are also annoying because by default they are not version controlled and land in a secret location.”
“which is terrible at contextualizing memory access and makes huge leaps that don’t make sense”
“still nowhere near good enough”
“It's conversely harmful when an agent manages it.”
“It inevitably ends up dragging in things that are unrelated and unimportant to the current task.”
“terrible at contextualizing memory access and makes huge leaps that don’t make sense”
“What I don't like about auto-memory is that Claude's behaviour towards me is diverging from how it behaves with the rest of my team.”
“I've also found that I have to give instructions like”
“the current memory system is too crude to be useful anyway”
“Memories are too verbose/specific/yet-generic for the value captured.”
“Memories have mostly been detrimental to me, I have disabled it completely after many moments of frustration.”
“I found Opus's 4.8 memories largely lacking value.”
“much more often harmful, pulling in obsolete info that muddies the waters about current tasks”
“they completely fail to capture intent”
“I’ve found the latter approach to work much, much better than simple”
“All the memories Claude created for me fell in the category remember-to-not-forget, so I disabled it altogether.”
“I get a lot of value out of simple things like memory for long-term project planning and task management”
“it's a much more casual and black box experience”
“Anthropic figured this out, their memory feature is a search not a memory that informs the personality/manipulates the current session.”
“the memory doesn't quite capture all the areas I'm interested in”
“it remembers the dimensions of my truck, so towing/loading questions don't need extra clarification.”
“I didn't want fragments of old conversations haunting new ones”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.