Long-term memory for Claude Desktop & Cursor, built on Kanerva's Sparse Distributed Memory — the associative model recent research proved equivalent to Transformer Attention. It recalls the meaning behind a vague prompt, even from noise.
100% open-source · Your memories never leave your machine · $5/mo optional cloud sync
Classic vector RAG is literal: no keyword overlap, no hit. SDM smears every fact across a 10,000-dimensional space and reconstructs the signal by majority vote inside the activation radius.
| Vector RAG | Holographic Memory (SDM) | |
|---|---|---|
| Match model | keyword / cosine | associative interference |
| Vague query | misses | reconstructs from noise |
| Conflicting facts | silently coexist | flagged as interference |
| Foundation | ad-hoc embeddings | Kanerva SDM ≈ Attention |
Declared over MCP (stdio). Each one does something a plain database can't.
Retrieve a de-noised "meaning cloud" from a vague or emotional cue — instantly remember context mentioned only in passing.
Store a fact with context, emotional valence, importance and tags, superposed across the association cloud.
Spot when a new fact contradicts an existing belief and surface it — "You moved? I had London on file."
Drop weak associations, reinforce frequent ones — keeps the store fast and free of clutter.
"You moved to Berlin? I remembered London — want me to update that?"
Interference detection makes the agent feel human — it notices when your story changes.
The engine is open-source and free forever. Pay only for convenience open code can't copy.
Free local mode needs no key. Add a license key only for encrypted cloud sync.
npx -y @smithery/cli install holographic-memory
{
"mcpServers": {
"holographic-memory": {
"command": "uvx",
"args": ["holographic-memory-server"],
"env": {
"MEMORY_MODE": "LOCAL",
"MEMORY_LICENSE_KEY": ""
}
}
}
} Notes on associative memory, the math behind it, and where it's going. Заметки об ассоциативной памяти, математике за ней и о том, куда всё движется.
Vector RAG matches on surface similarity: no shared keywords, no hit. It cannot connect "I dislike Python" to a later "what should I write this script in?" — the words don't overlap.
Read →Векторный RAG ищет по поверхностному сходству: нет общих слов — нет результата. Он не свяжет «не люблю Python» с более поздним «на чём написать скрипт?» — слова не пересекаются.
Читать →The engine is Kanerva's SDM, first described at MIT. Recent work (2021–2026) proved it is mathematically equivalent to the Attention mechanism inside Transformers — the very thing that powers GPT-4 and Claude.
Read →В основе — SDM Канервы, впервые описанная в MIT. Недавние работы (2021–2026) доказали её математическую эквивалентность механизму Attention в трансформерах — тому самому, на котором работают GPT-4 и Claude.
Читать →Kanerva designed SDM as a digital model of the cerebellum — the seat of motor skill. For narrow, motor tasks (walking, skating) that turns a weakness into a strength: repetition builds a stable interference pattern. The more it walks, the better it walks.
Read →Канерва задумывал SDM как цифровую модель мозжечка — центра моторики. Для узких моторных задач (ходьба, катание) это превращает минус в плюс: повторение формирует устойчивую интерференционную картину. Чем больше ходишь — тем лучше ходишь.
Читать →See all articles → Все статьи →
Want a live demo, a commercial license, or to build something together? Send a note. Нужна демонстрация, коммерческая лицензия или совместный проект? Напишите нам.