memvector/ext-memvector
MemVector: Local Vector API, Storage & Embedding Engine for PHP
This tool helps PHP developers build fast, local AI features like semantic search and content recommendations directly into their applications. It takes text or existing numeric vectors as input, processes them using small AI models running in the same PHP process, and outputs relevant results based on meaning. This is ideal for developers creating PHP applications that need efficient, private AI capabilities without relying on external services.
Use this if you are a PHP developer building high-performance applications that require local text embedding, vector search, or result reranking without external API calls or databases.
Not ideal if you need to work with very large generative AI models or if your PHP application's architecture cannot support long-lived processes that keep models loaded in memory.
Stars
15
Forks
—
Language
C++
License
MIT
Category
Last pushed
Mar 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/memvector/ext-memvector"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
alibaba/zvec
A lightweight, lightning-fast, in-process vector database
devflowinc/trieve
All-in-one platform for search, recommendations, RAG, and analytics offered via API
matte1782/edgevec
High-performance vector search for Browser, Node, and Edge
rryam/VecturaKit
Swift-based vector database for on-device RAG using MLTensor and MLX Embedders
KyroDB/KyroDB
Autonomous Vector database for AI agents and RAG. Hybrid Semantic Cache eliminates cold-cache...