antirez/neural-redis

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2228 stars · 100 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Redis loadable module (written in C) that implements feed-forward neural networks as a native Redis data type. It compresses data collection, training, and inference into a single in-server API with online training in background threads.

Use cases

• train a neural network inside redis
• simple classification and regression from user events
• predict which ad or promotion converts best
• online machine learning without a separate ML stack
• retrain a model as new data arrives in redis

When to choose

• you already run Redis and want lightweight, simple ML for small regression/classification tasks
• you want training and inference co-located with your data store
• you need fast-to-train fully connected networks with automatic normalization

When to avoid

• you need deep learning, CNNs, or RNNs for vision or sequence tasks
• you need an actively maintained project - the last release was 2018
• you need GPU acceleration or state-of-the-art model architectures

Facets

library · maturity abandoned

machine-learning database plugin-system machine-learning databases artificial-intelligence c self-hosted redis-module feedforward-neural-networks rprop online-training classification regression linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="antirez/neural-redis")