Total Recall
write-gated memory for Claude Code
Details
- External ID
- 46907183
- Source
- HN
- Company
- —
- Product
- Total Recall
- Website domain
- github.com
- Launched
- Feb. 5, 2026
- Cohort
- —
- Upvotes
- 67
- Upvotes percentile
- 0.8530997304582211
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
built this because I got tired of re-teaching Claude Code the same context every session. Preferences, decisions, “we already tried X,” “don’t touch this file,” etc. After a few days it starts to feel like onboarding the same coworker every morning.Most “agent memory” tools auto-save everything. That feels good briefly, then memory turns into a junk drawer and retrieval gets noisy. Total Recall takes the opposite approach: a write gate. Before anything gets promoted, it asks one question: “Will this change future behavior?” If not, it doesn’t get saved.How it works:Daily log first (raw notes)Promote durable stuff into registers (decisions, preferences, people, projects)Small working memory loads every session (kept intentionally lean)Hooks fail open. SessionStart can surface open loops + recent context. PreCompact writes to disk (not model-visible stdout)The holy shit moment is simple: tell Claude one important preference or decision once, come back tomorrow, and it behaves correctly without you repeating yourself.Would love feedback from heavy Claude Code users:Does the write gate feel right or too strict?Does this actually reduce repetition over multiple days?Any workflow/privacy footguns I’m missing?
Enrichment
- Theme
- utilities for Claude and Claude Code
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- memory for claude code
- Manually corrected
- False
Could you build this?
Yes Total Recall is a developer CLI/hook utility that manages a curated local context file or key-value store to gate persistent agent memory updates.
Discussion
20 comments analyzed.
Competitors mentioned: dory, MemoryLane, Claude Code (native infinite scroll search)
Concerns raised: AI slop in readmes hurting project discoverability, Concurrent sessions writing to same daily log simultaneously, Write gate consistency - model being overly conservative or permissive, Project-scoped memory creates redundancy across multiple projects, Automated memory degrades over time without human curation
Feature requests: Global layer for durable personal context plus project-scoped registers, Proactive surfacing of stale memories ("haven't referenced this in two weeks"), Per-session log files to avoid concurrent write conflicts, Remove-gates with automatic pruning suggestions, In-depth tutorial or comprehensive documentation
Competitors
Other products that read as similar to this one — 322 launches clear the similarity bar, closest 8 shown.
Attention rank: #62 of 323 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 85 days after the earliest competitor.
- Stop Claude Code from forgetting everything · hn · 2025-12-29 · 202 upvotes · similarity 0.63
- CodeYam Memory · hn · 2026-03-04 · 17 upvotes · similarity 0.63
- I built simple and efficient local memory system for Claude Code · hn · 2026-02-02 · 6 upvotes · similarity 0.61
- AI Memory Starter Kit · ph · 2026-09-21 · 2 upvotes · similarity 0.61
- A-MEM · hn · 2026-01-15 · 8 upvotes · similarity 0.56
- Claude-replay · hn · 2026-03-02 · 5 upvotes · similarity 0.55
- Agentmemory · ph · 2026-05-16 · 322 upvotes · similarity 0.55
- Claude Soul · hn · 2026-05-18 · 10 upvotes · similarity 0.53
Other launches for this product
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.