Self-hosted alternatives to zeroshot
200 self-hosted apps like zeroshot, closest match first.
Top picks
- J
- L
Lora Dataset Studio
LaunchSelf-hosted, one-tab workbench for the whole training lifecycle: build Character/Concept/Style datasets (generate, scrape, or triage a big dump in the Image Bank), curate, caption, clean watermarks, then train LoRAs on five model families o
Self-hosted
- G

Guaardvark
LaunchSelf-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local video, image, music and voice generation. No telemetry.
Self-hosted
- L

Locally Uncensored
LaunchThe all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. No Docker, no terminal, no cloud required.
Self-hosted
- C

CodeZero
LaunchOpen-source no-code automation platform for logistics, chatbots, and AI agents. Deploy on cloud, self-host, or hybrid with complete data sovereignty and modular workflow design.
Self-hosted
- L

LocalAI
LaunchLocalAI is an open-source, MIT-licensed AI engine that runs language models, speech, vision, image and video generation and agents on your own hardware. Its API is compatible with OpenAI, and the site says it also speaks the Anthropic, Olla
Self-hosted
More like zeroshot
Immich Swipe
Swipe right to keep photos, swipe left to delete them -> just like a dating app
About zeroshot

zeroshot
Efficient and simple image classification for developers
Zeroshot is an open source tool that lets developers build image classifiers from text descriptions instead of labelled training data. You describe your classes in a simple web interface, and it trains a custom model in a few minutes. You then install the Python package with pip or conda, create a classifier from your model's ID or path, preprocess an image and call predict to get the index of the predicted class. Models run locally on CPU or GPU, so classification works offline, has low latency and does not incur a charge each time it runs; the project claims it is faster and more accurate than OpenAI's CLIP. It is free, community-driven and aimed at developers who want to add computer vision to an app quickly. Documentation on getting started and how it works is on GitHub, and the project was built by contributors in San Francisco.
- Price
- Free
- Category
- Developer Tools
- Website
- usezeroshot.com



