automation

ODS: Run a Full AI Server on Your Own Machine

Launch LLM inference, chat UI, voice agents, RAG and image generation locally on PC, Mac or Linux—ideal for founders needing self‑hosted AI without cloud costs. 7.1k+ GitHub stars.

From the repo · “ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.”

7,629 stars+122★ this week1,073 forksPythonGuide quality 9/10 · reviewed Oct 8Updated 10/21/2026100% free · open source
What it does

Turn your computer into a local AI server for automation tasks, supporting features like LLM inference, chat UI, and image generation

When to use it
  • •You need to automate tasks on a local machine without relying on cloud services
  • •You want to prototype AI-powered applications with a low-cost, self-hosted solution
  • •Your project requires a high level of data privacy and security, making local deployment a necessity
Ready-to-paste prompt
ods-cli workflow run --workflow example-llm-inference --input 'What is the meaning of life?'
Heads up: Make sure you have Docker and Docker Compose installed on your system before attempting to run ODS, as it relies on containerization to manage its dependencies and services
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/ods && curl -fsSL https://workflowstacks.com/api/skills/ods/claude-skill -o ~/.claude/skills/ods/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How ODS: Run a Full AI Server on Your Own Machine works
Codeflow
Free to inspect

ODS: Run a Full AI Server on Your Own Machine is a very large Python project (~132k lines across 374 code files, plus 334 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~132k lines · 374 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
No API keys detected
Python 43%Shell 38%JavaScript 10%PowerShell 7%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    CLAUDE.md
    The instructions the AI actually follows
  3. 3
    ods/README.md
    Inside ods/ — the main logic begins here
What's in each folder
ods/Core code — the actual logic1247 files
installer/Folder47 files
.github/CI / automation (GitHub Actions)35 files
.claude/Editor / agent settings9 files
READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
Osmantic
Language
Python
Category
automation
Published
2/9/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/ods.svg)](https://workflowstacks.com/skills/ods?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.