jason/mempalace
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

README: AAAK works with local models too — Claude, GPT, Gemini, Llama, Mistral

Browse Source
This commit is contained in:
Milla Jovovich
2026-04-05 22:14:15 -07:00
committed by MSL
parent 18cca2c97c
commit f54d42f50a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -14,7 +14,7 @@ Other memory systems try to fix this by letting AI decide what's worth rememberi
**The Palace** — Ancient Greek orators memorized entire speeches by placing ideas in rooms of an imaginary building. Walk through the building, find the idea. MemPalace applies the same principle to AI memory: your conversations are organized into wings (people and projects), halls (types of memory), and rooms (specific ideas). No AI decides what matters — you keep every word, and the structure makes it searchable. That structure alone improves retrieval by 34%. **The Palace** — Ancient Greek orators memorized entire speeches by placing ideas in rooms of an imaginary building. Walk through the building, find the idea. MemPalace applies the same principle to AI memory: your conversations are organized into wings (people and projects), halls (types of memory), and rooms (specific ideas). No AI decides what matters — you keep every word, and the structure makes it searchable. That structure alone improves retrieval by 34%.
**AAAK** — To make all that data usable, MemPalace compresses it with AAAK — a lossless shorthand dialect designed for AI agents. Not meant to be read by humans — meant to be read by your AI, fast. 30x compression, zero information loss. Your AI loads months of context in ~120 tokens. Nothing else like it exists. **AAAK** — A lossless shorthand dialect designed for AI agents. Not meant to be read by humans — meant to be read by your AI, fast. 30x compression, zero information loss. Your AI loads months of context in ~120 tokens. And because AAAK is just structured text with a universal grammar, it works with **any model that reads text** — Claude, GPT, Gemini, Llama, Mistral. No decoder, no fine-tuning, no cloud API required. Run it against a local model and your entire memory stack stays offline. Nothing else like it exists.
**Local, open, adaptable** — MemPalace runs entirely on your machine, on any data you have locally, without using any external API or services. It has been tested on conversations — but it can be adapted for different types of datastores. This is why we're open-sourcing it. **Local, open, adaptable** — MemPalace runs entirely on your machine, on any data you have locally, without using any external API or services. It has been tested on conversations — but it can be adapted for different types of datastores. This is why we're open-sourcing it.
@@ -173,7 +173,7 @@ Your AI wakes up with L0 + L1 (~170 tokens) and knows your world. Searches only
### AAAK Compression ### AAAK Compression
AAAK is a lossless dialect — 30x compression, readable by any LLM without a decoder. AAAK is a lossless dialect — 30x compression, readable by any LLM without a decoder. It works with **Claude, GPT, Gemini, Llama, Mistral** — any model that reads text. Run it against a local Llama model and your whole memory stack stays offline.
**English (~1000 tokens):** **English (~1000 tokens):**
``` ```