redis/redis-vl-golang — explained in plain English
Analysis updated 2026-05-18
Build a retrieval pipeline that finds relevant documents by meaning using vector search.
Cache previous AI model responses in Redis to reduce repeated LLM calls and cost.
Give an AI agent persistent memory of past conversations stored in Redis.
Route incoming user queries to the right handler based on semantic similarity.
| redis/redis-vl-golang | eternal-flame-ad/mh-z19 | geohot/erigon | |
|---|---|---|---|
| Stars | 5 | 5 | 5 |
| Language | Go | Go | Go |
| Last pushed | — | 2019-03-31 | 2021-09-12 |
| Maintenance | — | Dormant | Dormant |
| Setup difficulty | easy | moderate | hard |
| Complexity | 3/5 | 2/5 | 4/5 |
| Audience | developer | developer | ops devops |
Figures from each repo's GitHub metadata at analysis time.
Requires Go 1.25+ and a running Redis 8+ instance, available via Docker or a free Redis Cloud tier.
Redis Vector Library for Go, known as RedisVL, is a Go programming language client for building AI applications on top of Redis, the popular in memory database. It is a Go version of an existing Python library from the same team, and it focuses on storing and searching vectors, which are the numeric representations that AI models use to capture the meaning of text, images, or other data. With this library a developer can define a schema describing what fields to store, such as text, tags, numbers, locations, and vector embeddings, either by writing a YAML file or by building the schema directly in Go code. Once a schema exists, the library creates a matching search index inside Redis and provides functions to load data in, fetch records back out by their key, and run several kinds of searches: pure vector similarity search, metadata filtering, full text keyword search, and hybrid searches that combine semantic and keyword signals together. Beyond basic search, the library includes features aimed specifically at AI workloads, such as caching previous AI responses to cut down on repeated calls to expensive language models, storing conversational memory for AI agents, and routing incoming queries to the right handler based on their meaning. It also ships with a command line tool for managing indexes from the terminal, connectors for several embedding providers, and tools that rerank search results to improve relevance. To use it, a developer needs Go version 1.25 or newer and a running Redis instance, which can be a free cloud tier, a local Docker container, or a self hosted enterprise deployment. It is released under the MIT license, meaning it can be used freely for any purpose, including commercial products, as long as the copyright notice is kept. The project currently has 5 stars.
A Go client library for storing and searching AI vector embeddings in Redis, used for retrieval, semantic caching, and agent memory.
Mainly Go. The stack also includes Go, Redis.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice (MIT license).
Setup difficulty is rated easy, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.