# tinyvector

> Pure Rust embedding database as lightweight Axum server for low-latency on-device vector search scaling to 100M+ vectors in memory. High accuracy/speed for edge RAG; simpler than Qdrant edge.

- **URL:** https://github.com/m1guelpf/tinyvector
- **Category:** Embedded & Edge Vector Databases
- **Tags:** Open Source, Rust, Lightweight, Embedded, No Server, In Memory, Edge Ai
- **Updated:** 2026-04-24 10:19
- **Canonical page:** https://vectordb.ever.works/items/tinyvector-m1guelpf

## Details

## Overview
tinyvector provides efficient on-device vector search.

## Features
- In-memory HNSW-like indexing
- Scales to 100M+ vectors
- Axum HTTP server

## Use Cases
- Edge document chat
- IoT website search
- Real-time CV

## Comparisons
- Tiny/simple vs Qdrant edge
- Better accuracy on medium datasets

## Pricing
Free open-source (MIT).

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/items/tinyvector-m1guelpf._