memory-keeper

99.9% DeepSeek cache hit, 3-tier context proxy

4 followers

99.9% DeepSeek cache hit, 3-tier context proxy

4 followers

Visit website

LghteihtNod.jsproy btwen penlw ad DeepSek AI. -tir rchvin fo 99.95%cace ht.

Overview
Reviews
Team
More

Free

Launch tags:Open Source•Developer Tools•GitHub

Launch Team

EneyProactive AI for Mac. Free test, 20,000 credits.

Promoted

Maker

📌

I built memory-keeper after watching my AI hallucinate constantly. OpenClaw's default context management was trimming 95% of messages, destroying DeepSeek's prompt cache. My cache hit rate was 14% — the AI was basically reading 4% of the conversation and guessing the rest. The fix was a 3-tier message archive that keeps the prefix stable. Now: 99.95% cache hit, <$0.001 per round, zero config changes. It's open source, 5 minutes to set up. Happy to answer any questions!

Report

3mo ago

Reviews