Lossless-memory
A personal AI memory that never summarizes
lossless-memory is a long-term memory system for a personal AI assistant that never summarizes. It keeps every raw line, timestamps everything, and searches by time first and words second, returning results in chronological order. A small index tells the model which topic the conversation is in, so context survives compaction and new sessions. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49786419
✨ The overview, FAQ and details below were drafted by AI from the product's own website and haven't been reviewed by the maker yet. Are you the maker? Claim this listing to review and edit them.
Overview
Who is it for?
Developers building a personal AI assistant that should remember what was actually said.
Problem
Most AI memory systems summarize or embed conversations, losing exactly what was said and when.
Solution
Store full logs on a time axis and retrieve by time phrases like "yesterday evening", then by keywords.
What makes it unique
No summaries ever; the author has run it daily for a single user since July 2026 and documents its failures too.
Lossless-memory FAQ
Does it summarize conversations?
No. Raw logs are kept in full and nothing is summarized.
How does search work?
Time phrases narrow the range and words rank results within it; results come back in chronological order with timestamps.
Details
- Pricing
- Open Source
- Categories
- LLMs & InfrastructureProductivity
- Built for
- Developers
Hunted by AI Launch Team
Discussion (0)
Sign in to join the discussion.