Skip to main content

Autonomous AI Coding Loop

Project description

Ralphy

A ralphy-implemented ralphy. This project was built using the original ralphy autonomous coding loop.

Autonomous AI Coding Loop that orchestrates AI coding assistants to implement tasks until completion.

Installation

pip install ralphy

Quick Start

# Initialize project config
ralphy --init

# Run a single task
ralphy "add user authentication"

# Run PRD until complete
ralphy --prd PRD.md

Features

  • Multiple AI Engines: Claude Code, OpenCode, Cursor, Codex, Qwen-Code, Factory Droid
  • PRD Mode: Loop through tasks from Markdown, YAML, or GitHub Issues
  • Single Task Mode: Execute one task in an existing project
  • Parallel Execution: Run tasks concurrently with git worktrees
  • Auto PR Creation: Create pull requests automatically
  • Cost Tracking: Monitor token usage and costs

Supported AI Engines

Engine Flag CLI
Claude Code --claude (default) claude
OpenCode --opencode opencode
Cursor Agent --cursor agent
Codex CLI --codex codex
Qwen-Code --qwen qwen
Factory Droid --droid droid

Configuration

Initialize a .ralphy/ directory with project config:

ralphy --init

This auto-detects:

  • Project name, language, framework
  • Test, lint, and build commands

Add rules the AI must follow:

ralphy --add-rule "Always use TypeScript strict mode"

PRD Formats

Markdown:

- [ ] Implement user authentication
- [ ] Add payment processing
- [x] Set up database (completed)

YAML:

tasks:
  - title: "Implement auth"
    parallel_group: 1
  - title: "Add payments"
    parallel_group: 1

GitHub Issues:

ralphy --github owner/repo --github-label enhancement

Options

ralphy --parallel              # Run tasks in parallel
ralphy --max-parallel 5        # Concurrent agents (default: 3)
ralphy --branch-per-task       # Create branch per task
ralphy --create-pr             # Create PRs automatically
ralphy --no-tests              # Skip tests
ralphy --no-lint               # Skip linting
ralphy --fast                  # Skip tests and linting
ralphy --max-iterations 10     # Stop after N tasks
ralphy --dry-run               # Preview without executing
ralphy --verbose               # Debug output

Requirements

  • Python 3.10+
  • git
  • At least one AI CLI installed (claude, opencode, etc.)

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ralphy-4.0.1.tar.gz (32.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ralphy-4.0.1-py3-none-any.whl (37.5 kB view details)

Uploaded Python 3

File details

Details for the file ralphy-4.0.1.tar.gz.

File metadata

  • Download URL: ralphy-4.0.1.tar.gz
  • Upload date:
  • Size: 32.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.16

File hashes

Hashes for ralphy-4.0.1.tar.gz
Algorithm Hash digest
SHA256 0e4b1f78420fd9bf607813f866a2ae3688273741ec19dbb09bd382f3186db04e
MD5 a154d17d3f16ad913cde7152ade266aa
BLAKE2b-256 ecb621a538d4ec8460efbb0b599673df19a3dd9fe69f26bbed60e5d918719215

See more details on using hashes here.

File details

Details for the file ralphy-4.0.1-py3-none-any.whl.

File metadata

  • Download URL: ralphy-4.0.1-py3-none-any.whl
  • Upload date:
  • Size: 37.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.16

File hashes

Hashes for ralphy-4.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 9debe4fa52ba937aa83f6559c56d3a71a4ad7d379f48613391a11c3ab4610612
MD5 5ae01c48644749a8d89fe9c38c5bf0bb
BLAKE2b-256 928ae7039c1c1ba19cd1b4282dabb4b46f80e96865eec23566e2c1ad4b0931ee

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page