Put your AI coding agent in a while True loop and let it ship.

Ralphify is a minimal CLI harness for autonomous AI coding loops. Pipe a prompt to an agent, validate with checks, repeat.

Get Started View Cookbook 
$ ralph init
Created ralph.toml + RALPH.md

$ ralph run -n 3
── Iteration 1 ──
✓ Iteration 1 completed (52.3s)
  Checks: 2 passed
    ✓ lint
    ✓ tests

── Iteration 2 ──
✗ Iteration 2 failed with exit code 1 (23.1s)
  Checks: 1 passed, 1 failed
    ✓ lint
    ✗ tests (exit 1)

── Iteration 3 ──
✓ Iteration 3 completed (41.7s)
  Checks: 2 passed
    ✓ lint
    ✓ tests

Done: 3 iteration(s) — 2 succeeded, 1 failed

Iteration 2 broke a test. Iteration 3 saw the failure and fixed it — that's the self-healing loop.

Install

uv tool install ralphify

Three primitives

Extend the basic loop with building blocks that live in .ralphify/

Checks

Run after each iteration to validate the agent's work. Failed check output feeds into the next iteration so the agent can fix its own mistakes.

Contexts

Inject dynamic data into the prompt before each iteration — git history, test status, API responses. The agent always sees fresh information.

Ralphs

Named, task-focused prompts you switch between at run time. Keep a docs ralph, a refactor ralph, and a bug-fix ralph.

Two commands to start

ralph init && ralph run
Read the guide