Claude Brain
Shares rank 9 of 20 agent memory systems by recommenders
A memory project for Claude Code that people say works well when CLAUDE.md tells the model when to save and search memories. Critics say it is a thin wrapper around Memvid, not an Anthropic product.
A memory project for Claude Code that people say works well when CLAUDE.md tells the model when to save and search memories. Critics say it is a thin wrapper around Memvid, not an Anthropic product.
13 people gave an opinion
- recommend it
- 6
- criticize it
- 7
- approval share
- 46%
Recommended in 3 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: not 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
- 6 people recommend itNeeds 10 or more, not met.
- 0.8 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 3 of 13 monthsNeeds 4 or more, not 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
Sloppy, vibe-coded writing and claims
“ugh the declarative short pseudo-sentence, markdown arrows everywhere, and asinine metaphors”
Comment from 19 Apr 2026 in “Claude Brain” “Boastful lies like this are a telltale sign of vibe-coded projects.”
Comment from 19 Apr 2026 in “Claude Brain” “Seems like vibe coded garbage”
Comment from 19 Apr 2026 in “Claude Brain” Overstated value, files are easy to save
“It just reads like someone who doesn't understand how to index and read data from a disk?”
Comment from 19 Apr 2026 in “Claude Brain” “As a sales pitch this is unconvincing. It's easy to save data a file.”
Comment from 19 Apr 2026 in “Claude Brain”
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 BrainThis page | 6 | 7 | 46% | 3 | — | — |
What people said
14 of the 15 comments that mention it, newest first. Each links to the original comment.
“telling the AI (via CLAUDE.md) to look for relevant memories and to think about when and how to save them has worked very well”
“Back then the consensus was that the idea was absurd”
“While the GitHub project is called "claude brain", it is not published by Anthropic and the repo is a thin wrapper around a service called "Memvid"”
“It's a wrapper round a ludicrously priced service”
“Boastful lies like this are a telltale sign of vibe-coded projects.”
“ugh the declarative short pseudo-sentence, markdown arrows everywhere, and asinine metaphors”
“Seems like vibe coded garbage”
“Conceptually cool, kinda how memory update process worked in TV Series "Travelers"”
“Except for the part where it gets added to the context window and sent to anthropic's servers?”
“It just reads like someone who doesn't understand how to index and read data from a disk?”
“As a sales pitch this is unconvincing. It's easy to save data a file.”
“Full lossless capture with search, not just checkpoints.”
“zero orphaned memories when projects move or rename”
“I wanted something faster than searching docs, and safer than auto-executing AI output.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.