AI tools · agent memory system
Lossless-memory
People recommend it as a personal AI memory that keeps full records, with useful versioned chronology. Caveat: relative time parsing is hardcoded for Japanese.
Summarized from 7 comments.
People recommend it as a personal AI memory that keeps full records, with useful versioned chronology. Caveat: relative time parsing is hardcoded for Japanese.
- recommend
- 6
- criticize
- 1
- months recommended
- 1 of 13
Why people love it
Clear design principles · 2
The part I like most is the LLL rule: "the AI reads it; the human writes it."
Sep 2026 · commentThe "never summarizes" choice matches what I've seen from the other side
Sep 2026 · comment
What people warn about
Will need other memory techniques · 1
eventually you'll hit a wall where this doesn't work, and you have to add another memory technique
Sep 2026 · commentMay break caching often · 1
Seems like this would break the cache often.
Sep 2026 · comment
What hackers pick instead
- EngrimOpen-source local memory engine for AI agents, built on SQLite, with local embeddings and no API key or external service needed. Critics note it is still limited by effective context size.21recommend
- MemPalacePeople recommend it as a locally managed memory layer for AI agents that retrieves past conversations well. Critics say independent end-to-end tests scored far below its retrieval benchmarks.9recommend
- GrovPeople recommend it for cutting exploration tokens and recalling past sessions for Claude Code. One user says it is rough around the edges, and it needs an API key.8recommend
- claude-memRecommended 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.8recommend
- LettaFree open-source agent framework with selective memory retrieval and long-context handling. Critics point to heavy dependencies and embedding API costs.8recommend
Every quote
The 7 most detailed of 7 comments. Each links to the original.
eventually you'll hit a wall where this doesn't work, and you have to add another memory technique
Mixed · Sep 2026 · in “Show HN: Lossless-memory – a personal AI memory that never summarizes”
The part I like most is the LLL rule: "the AI reads it; the human writes it."
Recommends · Sep 2026 · in “Show HN: Lossless-memory – a personal AI memory that never summarizes”
The "never summarizes" choice matches what I've seen from the other side
Recommends · Sep 2026 · in “Show HN: Lossless-memory – a personal AI memory that never summarizes”
Seems like this would break the cache often.
Mixed · Sep 2026 · in “Show HN: Lossless-memory – a personal AI memory that never summarizes”
temporal/versioned chronology is absolutely useful
Recommends · Sep 2026 · in “Show HN: Lossless-memory – a personal AI memory that never summarizes”
Its working pretty well to be honest!
Recommends · Sep 2026 · in “Show HN: Lossless-memory – a personal AI memory that never summarizes”
As long as the relative time parser is hardcoded for japanese, english sessions are stuck with manual ISO dates
Criticizes · Sep 2026 · in “Show HN: Lossless-memory – a personal AI memory that never summarizes”
Counts from 1,795,640 Hacker News comments, Nov 2025 to Nov 2026. How we count · Report a mistake