galdr

<p align="center">
  <img src="logo/Galdr_Logo_Big.jpg" alt="galdr banner" width="800">
</p>

<p align="center">
  <strong>Song magic for your codebase.</strong><br>
  Persistent memory, multi-repo orchestration, and adversarial quality gates for AI coding agents across every major IDE.
</p>

<p align="center">
  <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License: MIT"></a>
  <a href="CHANGELOG.md"><img src="https://img.shields.io/badge/version-1.2.0-green.svg" alt="Version"></a>
  <a href="https://www.python.org"><img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="Python 3.10+"></a>
  <a href="https://github.com/wrm3/galdr/releases"><img src="https://img.shields.io/github/v/release/wrm3/galdr?label=release" alt="Latest Release"></a>
  <a href="https://github.com/wrm3/galdr"><img src="https://img.shields.io/github/stars/wrm3/galdr?style=social" alt="GitHub stars"></a>
</p>

---

## The Problem

You have great AI coding agents. And they forget everything the moment you close the chat.

Session 1: You explain your architecture, your constraints, why you chose Postgres over Mongo.  
Session 12: The agent uses SQLite. Because it doesn't remember session 1.

You're running 4 repos — `api`, `web`, `mobile`, `shared-lib`. When something changes in `shared-lib`, every downstream repo needs to know. There's no mechanism for that. You copy-paste tasks manually. Half the time you forget.

You finish a feature and ask the same agent to verify it. It passes everything — of course it does, it wrote the code and knows what it *meant* to write. The bugs it introduced are invisible to it.

**galdr is the infrastructure layer that fixes all three of these.** It wraps around your AI IDEs and gives agents durable memory, cross-repo coordination, and adversarial quality enforcement — without changing how you code.

---

## What galdr gives your agents

**Persistent memory** — Architectural decisions, learned project conventions, se