SVDB
On-device vector database written in Swift, for semantic search inside apps.
View on GitHub ↗- Stars
- ★ 223
- Last commit
- 7 Dec 2025
- Maintenance
- Slowing
- Licence
- MIT
- Category
- On-device AI SDKs
- GitHub
- Dripfarm/SVDB
Overview
SVDB is a fast on-device vector database for Swift apps. You add documents with their embeddings to a collection and search them by similarity, all on the device. It is for developers building features that rely on on-device intelligence.
Features
- Stores documents and embedding vectors in named collections
- Similarity search over a collection
- Works with embeddings from any source, such as an OpenAI package or on-device models
- Includes a demo
Requirements
- Embeddings come from a separate source you provide
Install
Add the package in Xcode or Package.swift
.package(url: "https://github.com/Dripfarm/SVDB.git", from: "1.0.0")
Example
Create an "animals" collection, add an embedding for "cat", then search with the embedding for "dog" to find the closest matches.
Works with
Listed in
Read the code before you install anything. SwiftAgents doesn't review or endorse the tools listed here. Active: a commit in the last 90 days. Slowing: last commit within the past year. Stale: older than a year, or archived.