Ralph
Autonomous AI coding loop that repeatedly runs Amp or Claude Code until all PRD items are completed, using git history as memory.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Ralph, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Ralph is an open-source autonomous AI coding loop that repeatedly runs an AI coding tool (Amp CLI or Claude Code) until every item in a Product Requirements Document (PRD) is finished. Each iteration starts with clean context, while progress persists through git history and project files like prd.json and progress.txt. Ralph is designed to help developers ship features with minimal manual intervention by continuously planning, implementing, committing changes, and checking off PRD items in a structured loop.
Key features and capabilities
- autonomous coding
- prd workflow
- claude code
- amp cli
- git-based memory
- bash automation
- feature delivery
- prompt templates
Use cases
- Implementing PRD-driven features by running an autonomous coding loop until acceptance criteria are met.
- Automating multi-iteration coding work while keeping progress traceable through commits and PRD artifacts.
- Using Amp or Claude Code in a repeatable workflow with structured prompts and progress tracking.
- Speeding up feature delivery for side projects and internal tools with minimal supervision.