Ralphy – Autonomous AI Coding Loop

THE IDEA

Ralphy – Autonomous AI Coding Loop

Type: Software Status: In Development Tech Stack: Bash, Claude Code (CLI), Obsidian (Markdown/REST API), n8n (Docker mit PostgreSQL/Redis), Telegram Bot, Git Problem Statement AI code assistants like Claude Code require continuous human interaction and lose context after each session. For clearly specified development tasks (bug fixes, feature implementations, refactoring), this real-time accompaniment is unnecessary and inefficient. A framework is missing that runs AI development autonomously overnight, documents progress, escalates on blockers, and delivers finished results in the morning — like a night-shift developer. Description A framework for autonomous overnight AI development runs combining Claude Code (Ralph) with Obsidian and n8n. PRDs (Product Requirements Documents) are managed in Obsidian in a queue (Queue → Active → Done → Blocked). A shell script starts Claude Code iteratively in non-interactive mode, with each iteration receiving fresh context and ‚memory‘ stored in Git history, progress files, and learnings. Three n8n workflows control the process: Scheduler (time-triggered runs), Monitor (progress tracking), and Human-in-the-Loop (Telegram notifications on blockers). Use Case An AI programmer that automatically continues working on software projects overnight and delivers results in the morning. Link: https://github.com/rawk7000/Ralphy (private repo)