MiguelAxcar/ai-rpi-protocol

A lightweight protocol for AI-assisted coding that makes assistants research before planning and plan before coding. Drop one folder into any repo. In practice, this means fewer wrong implementations, fewer rewrites, and better decisions earlier. Works with Cursor, VS Code, Claude Code, Windsurf. Supports Claude, GPT, Gemini, Grok, Deepseek.

32
/ 100
Emerging

This project helps software developers and engineering teams make their AI coding assistants more reliable and effective. It provides a structured workflow that guides AI agents to research codebases, challenge assumptions, and validate work before generating solutions. Developers input coding tasks, and the AI produces better-grounded code, clearer PR reviews, and more thoughtful feature implementations.

Use this if you are a software developer or engineering lead experiencing unreliable or "too confident" outputs from your AI coding assistant, leading to frequent rewrites and extensive debugging.

Not ideal if you are looking for a new AI model, a specific IDE feature, or a CI/CD tool, as this project focuses on improving the workflow of existing AI coding assistants within your repository.

software-development code-review bug-fixing feature-implementation developer-productivity
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 11 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

License

MIT

Last pushed

Feb 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/MiguelAxcar/ai-rpi-protocol"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.