GitHub Repository

The memory layer that thinks like a human: remembers what matters, forgets what does not, and never calls home.

9 starsPython

Kore – local AI memory layer with Ebbinghaus forgetting curve

Name: Kore – local AI memory layer with Ebbinghaus forgetting curve
Availability: InStock
Author: juanauriti

by juanauriti·Feb 19, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainShip ItNiche Gem

Ebbinghaus decay + offline semantic search beats Mem0, Letta, Memori combined.

Strengths

•Genuine psychological model (forgetting curve) applied to memory pruning—not just novelty
•Fully local with zero API calls: sentence-transformers + SQLite FTS5 means real privacy
•Memory compression (cosine >0.88) + timeline API shows thoughtful design beyond basics

Weaknesses

•Unverified importance scoring heuristic (keywords/length) may not match user intent
•Early-stage (v0.3): only 17 passing tests, no deployed examples or agent integrations yet

Post Description

I built Kore because every AI memory tool I found either required cloud APIs, was too heavy, or stored everything forever with no pruning.

Kore is different: - Memory decay based on the Ebbinghaus forgetting curve — memories fade unless retrieved, with half-life based on importance (7 days for casual notes, 1 year for critical info) - Auto-importance scoring locally — no LLM call needed - Semantic search in 50+ languages — local sentence-transformers, zero API calls - Memory compression — auto-merges similar memories - Agent namespace isolation — multi-agent safe - Runs fully offline — SQLite + FTS5, FastAPI, no external services

pip install kore-memory[semantic] then kore to start.

Would love feedback on the decay formula and whether the Ebbinghaus approach makes sense for long-running agents.