claude-mem
Shares rank 5 of 20 agent memory systems by recommenders
Recommended as an open-source Claude Code memory plugin that recalls past prompts and replies without many tokens. One caveat: it only records from install forward.
Recommended as an open-source Claude Code memory plugin that recalls past prompts and replies without many tokens. One caveat: it only records from install forward.
11 people gave an opinion
- recommend it
- 8
- criticize it
- 3
- approval share
- 73%
Recommended in 6 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 8 people recommend itNeeds 10 or more, not met.
- 2.7 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 6 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.
Why people recommend it
Each mark is one comment
Replays past sessions' prompts and replies
“Pretty neat how it can go get individual prompts and replies from previous sessions without consuming a lot of tokens.”
Comment from 30 Dec 2025 in “Stop Claude Code from forgetting everything” “Great for replaying what happened.”
Comment from 15 Jan 2026 in “Show HN: A-MEM – Memory for Claude Code that links and evolves on its own” Low token use
“Pretty neat how it can go get individual prompts and replies from previous sessions without consuming a lot of tokens.”
Comment from 30 Dec 2025 in “Stop Claude Code from forgetting everything” “There are actually good tools to reduce token use”
Comment from 31 Mar 2026 in “Universal Claude.md – cut Claude output tokens by 63%”
What people warn about
Each mark is one comment
Heavy on tokens and context
“our context footprint is a fraction of what claude-mem has”
Comment from 5 May 2026 in “Show HN: Claude-smart – Make Claude Code self-improve from every session” “That's noisy and token-expensive.”
Comment from 18 Mar 2026 in “Engram – salience-gated memory for Claude Code (captures what matters)”
Other agent memory systems people recommend
The four most recommended other agent memory systems, 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 |
|---|---|---|---|---|---|---|
| Engrim | 21 | 0 | 100% | 4 | — | Approved |
| Total Recall for Claude Code | 12 | 4 | 75% | 5 | — | Approved |
| OKF Agent Memory | 9 | 3 | 75% | 3 | — | — |
| MemPalace | 9 | 8 | 53% | 3 | — | — |
| claude-memThis page | 8 | 3 | 73% | 6 | — | — |
What people said
10 of the 11 comments that mention it, newest first. Each links to the original comment.
“Try the claude-mem plugin.”
“no-op out of the box, only records forward from install”
“our context footprint is a fraction of what claude-mem has”
“There are actually good tools to reduce token use”
“This combination produces good results for me.”
“That's noisy and token-expensive.”
“great for solo continuity”
“open-source memory system for Claude Code”
“Great for replaying what happened.”
“Pretty neat how it can go get individual prompts and replies from previous sessions without consuming a lot of tokens.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.