Shodh-Memory: A Cognitive Memory System for Edge-Native AI Agents

Q: How is shodh-memory different from a vector database?

Vector databases give you similarity search. Shodh-memory gives you cognition — memories strengthen when accessed together (Hebbian learning), decay naturally over time (power-law forgetting), and form associative networks via a knowledge graph. It's the difference between storage and memory.

Q: Does shodh-memory require an internet connection?

No. Shodh-memory runs 100% offline. The embeddings, vector index, knowledge graph — everything runs locally. Perfect for edge devices, air-gapped systems, or anywhere you need data privacy.

Q: What's the memory overhead?

The binary is ~30MB. Models add ~50MB (22MB MiniLM embeddings + 14MB NER model + 14MB ONNX runtime). Each memory entry uses roughly 2-5KB. A system with 10,000 memories uses approximately 50MB of storage.

Q: Can shodh-memory run on a Raspberry Pi?

Yes. Shodh-memory is designed for edge deployment. It runs on Raspberry Pi Zero, Jetson Nano, industrial PCs, and other resource-constrained devices. Graph lookups are under 1 microsecond.

Q: How does memory decay work?

Shodh-memory uses a hybrid model: exponential decay for the first 3 days (consolidation phase), then power-law decay for long-term retention. Memories accessed 10+ times become potentiated and decay 10x slower. Based on Wixted & Ebbesen (1991).

Q: What is Hebbian learning in AI agent memory?

Cells that fire together, wire together. When memories are accessed together, their connection strengthens. When memories compete, interference effects occur. It's how biological brains work, now applied to AI agent memory.

Q: Is there a cloud version?

No, and that's intentional. Shodh-memory is built for local-first, privacy-preserving AI. Your agent's memories stay on your hardware. If you need multi-device sync, you can replicate the RocksDB storage yourself.

Q: What languages and frameworks does shodh-memory support?

The core is Rust. We provide: an MCP server (for Claude, Cursor, and other AI agents), Python bindings (via PyO3/maturin), and a REST API. The Rust crate can be embedded directly in your application.

Q: How do I contribute?

Check out github.com/varun29ankuS/shodh-memory. Open issues, submit PRs, or join discussions. The codebase is well-documented with 688+ tests. All constants have neuroscience citations.

Varun Sharma

doi:10.5281/zenodo.18668709

terms_of_service

Last updated: April 2026

// overview

Shodh-memory is open-source software licensed under the Apache License 2.0. By using our software or website, you agree to these terms.

// open-source software

The shodh-memory binary, MCP server, Python bindings, and TUI are provided under Apache 2.0
You may use, modify, and distribute the software freely under the license terms
The software is provided "as is" without warranty of any kind
We are not liable for any damages arising from use of the software
Attribution must be maintained as required by the Apache 2.0 license

// website usage

The shodh-memory.com website is for informational and promotional purposes
Blog content is licensed under CC BY 4.0 unless otherwise noted
You may not scrape, mirror, or redistribute the website without permission
We reserve the right to modify or discontinue any part of the website

// chat widget

The AI chat widget on this website uses Groq for inference. Messages you send are processed by third-party AI models. Do not share sensitive, confidential, or personally identifiable information through the chat widget. Chat data may be stored for support and product improvement purposes.

// your data

When you run shodh-memory locally, all data stays on your machine
We have no access to your memories, embeddings, or knowledge graphs
The software does not phone home, collect telemetry, or transmit data
You own your data completely — we make no claim to it

// trademarks

"Shodh" and "shodh-memory" are trademarks of the Shodh project. You may use these names to refer to the software, but not in a way that implies endorsement or affiliation without permission.

// limitation of liability

To the maximum extent permitted by law, shodh-memory and its contributors shall not be liable for any indirect, incidental, special, consequential, or punitive damages, or any loss of profits or data, whether in contract, tort, or otherwise, arising from use of the software or website.

// changes

We may update these terms from time to time. Continued use of the software or website constitutes acceptance of the updated terms. Material changes will be noted on this page.

// contact

Questions about these terms? Email us at enterprise@shodh-memory.com

tl;dr → Apache 2.0 for the code. Your data is yours. We're not liable for anything. Don't pretend to be us.