ODS
by Osmantic
ODS is an installer and control stack that sets up a private AI server on your own PC, Mac or Linux machine. It bundles local model inference, a chat web interface, workflow automation, image generation and document search so you can run AI without a cloud service.
- Stars
- 7.7k
- Licence
- Apache-2.0
- Runs on
- A small server
- Setup
- Moderate
- Language
- Python
- Age
- 263 days
What you can do with it
- Chat with open language models through a ChatGPT-style web interface on your own hardware
- Build automations and voice agents using bundled workflow tools such as n8n
- Search your own documents privately and generate images locally with ComfyUI
Make money with it
Offer to set up private, local AI assistants and automations for small firms that cannot send data to cloud services.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Run a private in-house AI assistant for staff so client documents never leave your own machine, avoiding per-seat subscription fees
- Automate repetitive tasks such as document handling, transcription and replies with local workflows instead of paid automation services
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Run a one-line install script on Linux or macOS (Docker required), or a PowerShell script on Windows that sets up WSL2, Ubuntu and Docker Desktop.
Follow the official instructions in the project README.
Things to check
- V3 pre-release: installers pull the current main branch, which is not a signed release
- Installer is run via curl piped to bash, so review the script first
- Needs about 40 GB free disk space and decent hardware; large models run slowly without a GPU
- Windows install needs a restart and administrator permission for WSL2 and Docker Desktop
Who's talking about it
Checked 31 Oct 2026. Summary drafted by AI from the project's README.
