automation

Agentic-OS: Automate AI Coding

Name: Agentic-OS: Automate AI Coding
Author: KbWen

Streamline AI coding with Agentic-OS, a governance framework, providing a structured workflow for coding agents.

103 stars25 forksPythonGuide quality 8/10Updated 7/27/2026100% free · open source

What it does

Agentic-os is a governance framework that automates a five-step workflow for AI coding agents, ensuring each step is completed with evidence.

When to use it

•When integrating multiple AI coding agents into your development pipeline
•When requiring a standardized workflow for AI-driven coding tasks
•When needing to ensure accountability and transparency in AI-assisted coding

Ready-to-paste prompt

Create an AGENTS.md file with the following content: `---
agents:
  - name: Claude Code
    plan: plan.md
    build: build.sh
    review: review.py
    test: test.py
    ship: ship.sh` and then run `agentic-os run` to execute the workflow

Heads up: Ensure that you have Python installed on your system, as agentic-os is built using Python, and also be aware that you need to define your AI coding agents and workflow steps in the AGENTS.md file before running the agentic-os workflow

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/agentic-os && curl -fsSL https://workflowstacks.com/api/skills/agentic-os/claude-skill -o ~/.claude/skills/agentic-os/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 Agentic-OS: Automate AI Coding works

Codeflow

Free to inspect

Agentic-OS: Automate AI Coding is a large Python project (~22k lines across 54 code files, plus 68 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, MIT license, has a test suite.

Size

Large codebase

~22k lines · 54 code files · ~3 h to skim

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 74%Shell 15%PowerShell 11%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
demo/render_concept_hero.py
A worked example — copy this to get going

What's in each folder

docs/Documentation92 files

demo/Examples you can copy9 files

installers/Folder3 files

codex/Folder1 files

.agentcortex/Tool / agent settings307 files

.agent/Tool / agent settings57 files

tests/Tests — proof it works56 files

.claude/Editor / agent settings36 files

READMEHas testsDocumentedCI checksExamples includedMIT licenseUpdated this month