Recall

AI

memory for coding assistants

SHOW HN2025

171points
93comments
#409of 3,837 in 2025
Top 11%of 2025 by points

How HN took it

RoastedHalf or more of the comments are critical

2 positive, 18 neutral or asking, 0 mixed, 20 critical, out of 40 comments about the project. Thread score -0.41.

Idea: 1 for, 12 againstExecution: 0 for, 3 againstDesign: 0 for, 2 againstPerformance: 0 for, 1 againstPrivacy: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Useful for reducing context loss after compaction

    From 1 comment
    • I've been using it for a while now, personally. I've found that I have less issues with context, I can easily recall (pun intended) after a context compact, etc.
      elfenleid on HN

Objections

  • Claude Code already has native memory via CLAUDE.md and /memory

    From 3 comments
    • Memory features are useful for the same reason that a human would use a database instead of a large .md file: it's more efficient to query for something and get exactly what you…
      steveklabnik on HN
    • It's had native memory in the form of per-directory CLAUDE.md files for a while though. Not just 2.0
      atonse on HN
    • Claude’s memory function adds a note to the file(s) that it reads on startup. Whereas this tool pulls from a database of memories on-demand.
      ebcode on HN
  • Too many tools (27) bloat the context window

    From 1 comment
    • Why would you bloat the (already crowded) context window with 27 tools instead of the 2 simplest ones: Save Memory & Search Memory? Or even just search, handling the save process…
      pacoWebConsult on HN
  • Distribution via npm is a non-starter for some

    From 1 comment
    • A great hack/shortcut for solving this "memory" problem is to have a rolling RAG KB. You don't fill up the context, and you can use a re-ranking model to further improve…
      btbuildem on HN
  • Prompt injection risk from persistent memory

    From 1 comment
    • Every single persistent memory feature is a persistence vector for prompt injection.
      gmerc on HN

Requests

  • Support for Valkey

    From 1 comment
  • Simpler design with fewer tools

    From 1 comment
    • Why would you bloat the (already crowded) context window with 27 tools instead of the 2 simplest ones: Save Memory & Search Memory? Or even just search, handling the save process…
      pacoWebConsult on HN

Questions

  • How does Claude know when to store or recall memories?

    From 2 comments
    • How does Claude know when to try and remember? Often memory works too well and crowds out new things, so how are you balancing that?
      datadrivenangel on HN
    • The problem is you need to tell prompt Claude to "Store" or "Remember", if you don't it will never call the MCP server. Ideally, Claude would have some mechanism to store…
      asdev on HN
  • How was it benchmarked against a plain text file?

    From 1 comment
    • how did you benchmark this against much less convoluted solutions, like "a text file"? how much better was this to justify all that extra complexity?
      bananapub on HN

Alternatives named

  • Claude's native CLAUDE.md and /memory feature

    From 2 comments
    • Memory features are useful for the same reason that a human would use a database instead of a large .md file: it's more efficient to query for something and get exactly what you…
      steveklabnik on HN
    • It's had native memory in the form of per-directory CLAUDE.md files for a while though. Not just 2.0
      atonse on HN
  • Claude API memory tool

    From 1 comment
    • They do, new feature, not available in claude code but via API headers. https://docs.claude.com/en/docs/agents-and-tools/tool-use/memory-tool
      _joel on HN
  • Markdown context files like SpecKit

    From 1 comment
    • Why would you not use context files in form of .md? E.g. how the SpecKit project does it.
      bryanhogan on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/45516584)