---
title: ".pi, my context configuration for Pi"
description: "My Pi context configuration, its public part: compact agent norms (responsibility, contracts, execution, tech stacks), injected through pi-⁠context-⁠tree."
url: "https://mc-stud.io/en/open-source/pi-config"
lang: "en"
updated: "2026-10-12"
---

Experimental Pi context norms configuration

# .pi

My Pi context configuration, its public part: compact agent norms (responsibility, contracts, execution, tech stacks), injected through pi-⁠context-⁠tree.

Install

`git clone https://github.com/ZEDIUM-Off/.pi.git ~/pi-config`

Young tools: read the repository README before installing.

**9** commits / 12 months

**Latest version**

v0.1.0

**star**

1

**forks**

0

**contributor**

1

**open issues**

0

**Last commit**

11 October 2026

Commits per month. Last 12 months, each repository on its own scale.

GitHub figures taken on 12 October 2026.

**Source code**

[github.com/ZEDIUM-Off/.pi](https://github.com/ZEDIUM-Off/.pi)

**Licence**

MIT licence

**Status**

Experimental

## What it does

This repository publishes the shareable part of my Pi configuration. It holds a `CONTEXT.json` and a set of compact norms: general principles, responsibility, contracts, agent behaviour, execution flow, and rules per tech stack (TypeScript, web, systems). pi-context-tree injects them at the right time.

It is public by default, with an allowlist of publishable files; no credentials are synced. Clone it separately to take inspiration, rather than over an existing setup: the README covers both cases.

[Source code](https://github.com/ZEDIUM-Off/.pi)

## When to reach for it

- You want a concrete example of short, versioned agent norms.
- You want to structure deterministic, auditable context in your own setup.

## Let’s talk about what AI could change for you

A 30-minute discovery call, by video and with no commitment, to talk about your project, your constraints and the best next step.

[Book a call](https://calendar.app.google/VQTPrCgNvQSNwdA7A)

[contact@mc-stud.io](mailto:contact@mc-stud.io?subject=First%20call)