Sisi

Visit Tool

sisi is an Open Source CLI tool for semantic image search. It allows users to search images locally without third-party APIs, powered by node-mlx.

Claim this tool

No Views Yet

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is sisi?

sisi is a free, open-source command-line interface (CLI) tool designed for semantic image search. It enables users to perform image searches locally on their machines, eliminating the need for external APIs. The tool is powered by node-mlx, a machine learning framework built for Node.js, and leverages the CLIP model to compute image embeddings. sisi supports Macs with Apple Silicon and x64/arm64 Linux, though Windows support is not yet available. It allows users to build and update image indexes for specified directories, list indexed directories, remove indexes, and search for images using natural language queries or image URLs/local files. The indexing process can be time-consuming for large collections without GPU support, but subsequent updates are faster as it only processes new or modified files.

Best used for

Ideal for photographers and developers who need to quickly find specific images within large local collections, organize personal photo libraries, and search by image content rather than just filenames or tags. Especially valuable for those who prefer command-line tools and local processing for privacy and speed.

Common actions

search images

organize photos

find visual content

open-sourceworkflowsdeepfakeautomated workflow"AI Agents"low-code/no-codeface swappingcollaborationgithub copilot

Capabilities

Key features

Semantic image search
Local indexing
CLI interface
CLIP model integration
GPU/CPU support
Index management

Target Audience

photographer

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What operating systems does sisi support?

sisi currently supports Macs with Apple Silicon and x64/arm64 Linux. There is no support for Windows yet, but the developer might explore making MLX work on it in the future to enable Windows compatibility.

How does sisi perform image searches without third-party APIs?

sisi builds an index by computing embeddings of images using the CLIP model locally on your machine. When you search, it computes cosine similarities between your query string and these stored embeddings, all without relying on external services.

Is GPU required for sisi to work efficiently?

While sisi works on both GPU (Apple Silicon Macs) and CPU (x64 Macs, x64/arm64 Linux), GPU support significantly speeds up the initial indexing process. Without a GPU, indexing tens of thousands of images can take many hours, though subsequent updates are faster.

Trending

Subcategories trending in Research & Education

Academic Research Study Assistants Knowledge Management Course Creation Scientific Computing Summarization

Trending

Also listed in

This tool also appears in

Coding & Development › Open Source & Models Content & Design › Photo Editing

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce