Show HN: MemX – Shared memory for LLM agents

[mmmehulll]

Hey everyone — I built this and wanted to share as its free to use and might help some of you:

https://mem-x.vercel.app

GH: https://github.com/MehulG/memX

memX is a shared memory layer for LLM agents — kind of like Redis, but with real-time sync, pub/sub, schema validation, and access control.

Instead of having agents pass messages or follow a fixed pipeline, they just read and write to shared memory keys. It’s like a collaborative whiteboard where agents evolve context together.

Key features:

Real-time pub/sub

Per-key JSON schema validation

API key-based ACLs

Python SDK

Would love to hear how folks here are managing shared state or context across autonomous agents.