MemPalace
The highest-scoring AI memory system ever benchmarked. And it's free.
Every conversation you have with an AI — every decision, every debugging session, every architecture debate — disappears when the session ends. Six months of work, gone. You start over every time.
Other memory systems try to fix this by letting AI decide what's worth remembering. It extracts "user prefers Postgres" and throws away the conversation where you explained why. MemPalace takes a different approach: store everything, then make it findable.
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 — 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.
[![][version-shield]][release-link]
[![][python-shield]][python-link]
[![][license-shield]][license-link]
[![][discord-shield]][discord-link]
Quick Start · The Palace · AAAK Dialect · Benchmarks · MCP Tools
Highest LongMemEval score ever published — free or paid.
96.6%
LongMemEval R@5
Zero API calls | 100%
LongMemEval R@5
with Haiku rerank | +34%
Retrieval boost
from palace structure | $0
No subscription
No cloud. Local only. |
Reproducible — runners in benchmarks/. Full results.
Quick Start
pip install mempalace
# Set up your world — who you work with, what your projects are
mempalace init ~/projects/myapp
# Mine your data
mempalace mine ~/projects/myapp # projects — code, docs, notes
mempalace mine ~/chats/ --mode convos # convos — Claude, ChatGPT, Slack exports
mempalace mine ~/chats/ --mode convos --extract general # general — classifies into decisions, milestones, problems
# Search anything you've ever discussed
mempalace search "why did we switch to GraphQL"
# Your AI remembers
mempalace status
Three mining modes: projects (code and docs), convos (conversation exports), and general (auto-classifies into decisions, preferences, milestones, problems, and emotional context). Everything stays on your machine.
How You Actually Use It
After the one-time setup (install → init → mine), you don't run MemPalace commands manually. Your AI uses it for you. There are two ways, depending on which AI you use.
With Claude, ChatGPT, Cursor (MCP-compatible tools)
# Connect MemPalace once
claude mcp add mempalace -- python -m mempalace.mcp_server
Now your AI has 19 tools available through MCP. Ask it anything:
"What did we decide about auth last month?"
Claude calls mempalace_search automatically, gets verbatim results, and answers you. You never type mempalace search again. The AI handles it.
If you want a repeatable Claude import that only keeps chat transcripts, use scripts/import_claude_jsonl.sh. It filters the source tree down to *.jsonl files before calling the existing conversation miner.
With local models (Llama, Mistral, or any offline LLM)
Local models generally don't speak MCP yet. Two approaches:
1. Wake-up command — load your world into the model's context:
mempalace wake-up > context.txt
# Paste context.txt into your local model's system prompt
This gives your local model ~170 tokens of critical facts (in AAAK if you prefer) before you ask a single question.
2. CLI search — query on demand, feed results into your prompt:
