Skip to main content

ralph-workflow

Ralph Workflow is a free, open-source AI agent orchestrator for coding work. You give it one well-specified task; it runs a Ralph loop (plan → build → verify → fix) with your chosen coding agent, then you come back to inspect the result. Adopt the default workflow as-is first; extend it later.

It fits developers and small teams with work that is too big to babysit and too risky to trust blindly. It is not for vague prompts or repos without tests or other guardrails.

Install

pipx install ralph-workflow
ralph --version

pipx keeps the install isolated from your other Python projects; the post-condition is that ralph --version prints the installed package version. pip install ralph-workflow also works.

First run

  1. Install Ralph Workflow (pipx or pip, above).
  2. In your project: ralph --init — creates user-global config and a starter PROMPT.md; it does not create .agent/. Advanced project-local overrides are explicit opt-in via ralph --init-local-config (alias: ralph --generate-local-config).
  3. Confirm a supported agent CLI is on your PATH and authenticated (ralph --list-agents).
  4. Run ralph --diagnose and fix any reported problem until every line is green.
  5. Edit PROMPT.md with the outcome and checks you expect. Remove the <!-- ralph:starter-prompt ... --> sentinel at the top — Ralph Workflow refuses to run while it remains. Or, before PROMPT.md exists, seed a task-shaped starter with ralph --init feature-spec, guardrail, refactor, test-coverage, or docs.
  6. Run ralph. When it finishes, read the summary of what changed and which checks passed, then verify the feature yourself.

The canonical first-run walkthrough is Getting started. For agent-specific model-string formats, see Agent compatibility. For configuration after the first run, open the operator manual.

Supported agents

Eight built-in agents ship with Ralph Workflow:

Agent Notes
Claude Code Anthropic's CLI for Claude (interactive, PTY transport).
Claude Code (Headless) Same claude binary in headless subprocess mode (claude-headless).
Codex OpenAI's Codex CLI.
OpenCode Open-source terminal coding agent.
Nanocoder Local-only TUI coding agent.
Google Anti Gravity (AGY) Google's Antigravity CLI (agy). Re-check after AGY updates.
Pi Minimal coding agent. Headless mode is pi --mode json <prompt>.
Cursor Cursor Agent CLI (agent), headless --print mode.

Pick one, authenticate it on your machine once, and Ralph Workflow uses it. Selection and trust-boundary details are in agents and agent-compatibility.

Requirements

  • Python ≥ 3.12
  • Local execution; no daemon, no cloud dependency
  • One supported agent CLI installed and authenticated

License

AGPL-3.0-or-later.

Documentation

The maintained operator manual is at docs/sphinx/index.rst — tutorial, configuration reference, MCP / artifact / pipeline configuration, concepts, troubleshooting, diagnostics, and developer internals.

Project home

Download files

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

Source Distribution

ralph_workflow-0.9.9.tar.gz (2.2 MB view details)

Uploaded Source

Built Distribution

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

ralph_workflow-0.9.9-py3-none-any.whl (2.9 MB view details)

Uploaded Python 3

File details

Details for the file ralph_workflow-0.9.9.tar.gz.

File metadata

  • Download URL: ralph_workflow-0.9.9.tar.gz
  • Upload date:
  • Size: 2.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.14.5

File hashes

Hashes for ralph_workflow-0.9.9.tar.gz
Algorithm Hash digest
SHA256 7903d8de8daa039544b566d31023c8c1fb1ecc05c1729b2e0ffe3af7c03098e4
MD5 5ba5cd548424da1adf2e3b7dd2dd4487
BLAKE2b-256 2e6b4803bb8746b1fa07564c7ae213ada25d9a3782bf393aaf2a4f17be064af0

See more details on using hashes here.

File details

Details for the file ralph_workflow-0.9.9-py3-none-any.whl.

File metadata

  • Download URL: ralph_workflow-0.9.9-py3-none-any.whl
  • Upload date:
  • Size: 2.9 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.14.5

File hashes

Hashes for ralph_workflow-0.9.9-py3-none-any.whl
Algorithm Hash digest
SHA256 210e5e067289d94b320e209f6861d8d872c45853a1ba1527be1476e44df8f641
MD5 ee89b8b0cd933aad69fec66b617a18cd
BLAKE2b-256 e90b532f33c67843839080287b91cd54492d4b8622d97c1a03ee8fa8ea5b1f6b

See more details on using hashes here.

Release history Release notifications | RSS feed

0.9.27

2 files

0.9.26

2 files

0.9.25

2 files

0.9.24

2 files

0.9.23

2 files

0.9.21

2 files

0.9.20

2 files

0.9.19

2 files

0.9.18

2 files

0.9.17

2 files

0.9.16

2 files

0.9.15

2 files

0.9.14

2 files

0.9.13

2 files

0.9.12

2 files

0.9.11

2 files

0.9.10

2 files

This release

0.9.9 This release

2 files

0.9.8

2 files

0.9.7

2 files

0.9.6

2 files

0.9.5

2 files

0.9.4

2 files

0.9.3

2 files

0.9.1

2 files

0.9.0

2 files

0.8.27

2 files

0.8.25

2 files

0.8.24

2 files

0.8.23

2 files

0.8.22

2 files

0.8.21

2 files

0.8.20

2 files

0.8.19

2 files

0.8.18

2 files

0.8.17

2 files

0.8.16

2 files

0.8.15

2 files

0.8.14

2 files

0.8.13

2 files

0.8.12

2 files

0.8.11

2 files

0.8.10

2 files

0.8.9

2 files

0.8.8

2 files

0.8.7

2 files

0.8.6

2 files

0.8.5

2 files

0.8.4

2 files

0.8.3

2 files

0.8.2

2 files

0.8.1

2 files

0.8.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page