Ralpher
A CLI tool that orchestrates Claude Code for autonomous software development. Give it a prompt, and it generates a Project Plan, breaks it into tasks, then runs iterative Claude development loops to implement each one.
Workflow: User Prompt ➔ Project Plan ➔ Ralph Wiggum Loop
Install
pipx install ralpher
Usage
# 1. Generate a Project Plan
ralpher plan "Create a TODO app" --name todo-app
# (Optional) Refine the plan
ralpher refine "Use MySQL"
# 2. Run the Ralph-loop on an existing plan
ralpher loop
How it works
- Plan generation -- Sends your prompt to Claude to produce a structured Project Plan with tasks, saved to
.claude/ralpher/projects/{project_id}/PLAN.md. - Run Ralph-loop
- Parses the plan into a structured JSON model (project, tasks with acceptance criteria and priorities).
- Iteratively invokes
claudeto implement each task on a dedicated git branch (ralph/{project_id}), tracking progress and detecting completion.
Notion integration
Ralpher supports optional Notion integration for syncing task status. Set these in a .env file:
RALPHER_NOTION_TOKEN-- Notion API tokenRALPHER_NOTION_PARENT_PAGE_ID-- Parent page for task pages
Development
# Run tests
uv run pytest
TODO
- Add git worktree support
- Create PRs automatically
- Run repeating tasks in a loop (useful for continuous optimization, refactoring, or research)
- Implement a standalone reviewer agent (or subagent) in both the planning and loop stages
- Support Gemini-CLI
- Support Codex CLI
Acknowledgements
This project draws its design and some of its prompts from snarktank/ralph.
Metadata
Release files for ralpher 0.1.6
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ralpher-0.1.6.tar.gz | 59.0 kB | Without provenance | Details for ralpher-0.1.6.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ralpher-0.1.6-py3-none-any.whl | Python 3 | none | any | Details for ralpher-0.1.6-py3-none-any.whl |
Total release size: 98.4 kB
Release files / ralpher-0.1.6.tar.gz
| Download URL | ralpher-0.1.6.tar.gz |
|---|---|
| Size | 59.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3559113db475d2f98851e94e3dec9efc9de63d214c07b260d95fbdfa3207f18c
|
|
BLAKE2b-256 checksum How to use checksums |
5a7961163604b4b861be2a8f9f21d5f559954759fbd7f266bc2db67a8123fc63
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.3 {"installer":{"name":"uv","version":"0.11.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / ralpher-0.1.6-py3-none-any.whl
| Download URL | ralpher-0.1.6-py3-none-any.whl |
|---|---|
| Size | 39.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
425a3eacfb084744da2ca993de4f5bc467af9ac5f6b585f0c5d0d18484fc68c3
|
|
BLAKE2b-256 checksum How to use checksums |
e811f56fba62f58f59b4116f81f2b9075dbb33f4b544668f1b324f7333360fb7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.3 {"installer":{"name":"uv","version":"0.11.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for ralpher 0.1.6
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.