Back to browse
GitHub Repository

The highest-scoring AI memory system ever benchmarked. And it's free.

0 starsPython

MemPalace Agent that sits in front of any LLM endpoint and gives memory

by modinfo·Apr 16, 2026·1 point·0 comments

AI Analysis

●●SolidBig BrainDark Horse

96.6% LongMemEval score using verbatim storage instead of AI summarization.

Strengths
  • Raw verbatim storage achieves 96.6% LongMemEval without API calls
  • Memory palace structure organizes conversations into wings, halls, rooms
  • Runs entirely local with no external API dependencies or cloud services
Weaknesses
  • LLM memory category increasingly crowded with Mem0, Zep, LangChain
  • AAAK compression dialect experimental and currently regresses benchmark scores
Category
Target Audience

Developers building LLM applications with persistent memory

Similar To

Mem0 · Zep · LangChain Memory

Similar Projects

AI/MLMid

Tiny project memory for coding agents

Structured context files for agents when Cursor rules and Continue configs already exist.

Ship It
SevenQin
101mo ago
AI/ML●●Solid

Memv – Memory for AI Agents

Predict-calibrate extraction reduces noise, but Zep and Mem0 already dominate the agent memory space.

Big BrainNiche Gem
brgsk
433mo ago