Total Recall for Claude Code
Hacker ApprovedRanked 2 of 20 agent memory systems by recommenders
Recommended as a write-gated memory layer for Claude Code that keeps only entries worth saving, so past decisions and conversations stay searchable.
Recommended as a write-gated memory layer for Claude Code that keeps only entries worth saving, so past decisions and conversations stay searchable.
16 people gave an opinion
- recommend it
- 12
- criticize it
- 4
- approval share
- 75%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 12 people recommend itNeeds 10 or more, met.
- 3 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 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
Write gate keeps memory from bloating
“I actually prefer that direction since saving too much degrades the whole system over time”
Comment from 10 Feb 2026 in “Show HN: Total Recall – write-gated memory for Claude Code” “Total Recall's approach of a 'write gate' is exactly what we need”
Comment from 6 Feb 2026 in “Show HN: Total Recall – write-gated memory for Claude Code” “Total Recall takes the opposite approach: a write gate.”
Comment from 5 Feb 2026 in “Show HN: Total Recall – write-gated memory for Claude Code” - Comment from 9 Feb 2026 in “Show HN: Total Recall – write-gated memory for Claude Code”
Works well in daily use
“So it seems to work quite well, as it’s been dogfooding itself for the past month”
Comment from 29 Jun 2026 in “Lore – give your coding agent the decisions your team made” “It has made it so it doesn't matter what I built where (or when)”
Comment from 8 Jul 2026 in “GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday” “it is doing it work as intended without getting in the way”
Comment from 6 Feb 2026 in “Show HN: Total Recall – write-gated memory for Claude Code” Daily-log-first approach is well designed
“the daily-log-first approach is a smart design choice”
Comment from 10 Feb 2026 in “Show HN: Total Recall – write-gated memory for Claude Code” “Nice work - the daily-log-first approach resonates”
Comment from 10 Feb 2026 in “Show HN: Total Recall – write-gated memory for Claude Code” Searchable history of past conversations
“The CLI I added here is very exciting, you can ask some interesting questions about your interactions with the AI.”
Comment from 23 Dec 2025 in “Total Recall: RAG Search Across All Your Claude Code and Codex Conversations” “It has made it so it doesn't matter what I built where (or when)”
Comment from 8 Jul 2026 in “GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday”
What people warn about
Each mark is one comment
Verbose, repetitive, token-expensive output
“It's clearly an LLM dump that repeats a lot of the same points multiple times”
Comment from 10 Feb 2026 in “Show HN: Total Recall – write-gated memory for Claude Code” “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 CodeThis page | 12 | 4 | 75% | 5 | — | Approved |
| OKF Agent Memory | 9 | 3 | 75% | 3 | — | — |
| MemPalace | 9 | 8 | 53% | 3 | — | — |
| Grov | 8 | 0 | 100% | 6 | — | — |
What people said
15 of the 19 comments that mention it, newest first. Each links to the original comment.
“It was lazy when Morpheus used it just as it was lazy when Dr. Edgemar used it in Total Recall.”
“It has made it so it doesn't matter what I built where (or when)”
“So it seems to work quite well, as it’s been dogfooding itself for the past month”
“That's noisy and token-expensive.”
“I actually prefer that direction since saving too much degrades the whole system over time”
“Nice work - the daily-log-first approach resonates”
“the daily-log-first approach is a smart design choice”
“I want an in-depth tutorial, so I can really wrap my head around it, because it blows my mind!”
“It's clearly an LLM dump that repeats a lot of the same points multiple times”
“The gate is definitely the right abstraction.”
“Love the idea and the approach, both. Intend to try it.”
“it is doing it work as intended without getting in the way”
“Total Recall's approach of a 'write gate' is exactly what we need”
“Total Recall takes the opposite approach: a write gate.”
“The CLI I added here is very exciting, you can ask some interesting questions about your interactions with the AI.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.