Shodh Memory

Neuroscience-inspired offline memory engine for AI agents

Pluginfreeglobal

Shodh Memory is an offline memory engine for AI agents that combines Hebbian learning and a knowledge graph so memories strengthen with use and decay realistically, instead of relying on static vector search. It ships as a small, dependency-free binary suited to edge deployments like robotics or air-gapped systems, and integrates with frameworks like Claude and Cursor. It's open source and free to use.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Shodh Memory - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Shodh Memory to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Shodh Memory (or something else) actually fits.

Try a problem