#4040th of 52 in Coding agents and assistants

ralph-claude-code

Shell loop that reruns Claude Code until a task list is finished

Stars: 9.7k
License: MIT
Last commit: Oct 2026
Language: Shell

Missed the latest GitHub check; these facts may be older.

Overview

Ralph is a set of shell commands that re-runs Claude Code in a loop against a PROMPT.md and a fix_plan.md task list until the work is done. It exits only when heuristic completion indicators and an explicit EXIT_SIGNAL both agree. It adds rate limiting (100 calls/hour by default), a circuit breaker, session resume and a tmux monitor. Projects are set up with ralph-enable, ralph-import or ralph-setup.

Who it is for: Developers running Claude Code unattended on task-list-driven builds

Strengths

Dual-condition exit gate (indicators plus EXIT_SIGNAL) reduces premature stops
Rate limit, circuit breaker and 5-hour API limit handling for unattended runs
Imports tasks from PRDs, GitHub issues or beads; ralph-enable detects project type
Optional Docker and E2B sandbox execution; 784 tests reported

Weaknesses

Tied to the claude CLI; multi-provider support is still in progress
Breaking changes between versions, including .ralph/ layout and .ralphrc parsing
No tagged releases on the repository
Exit detection relies partly on heuristics; loops consume API quota

What it needs

no GPU
Docker
Needs Claude Code CLI, tmux, git, Docker (optional), E2B (optional)
Models: Claude (via Claude Code)

Also in Coding agents and assistants

See all 52

Also in Coding agents and assistants
Rank	Project	Score
1	claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs194.9k starsMIT	83 out of 100
2	opencodeTerminal coding agent with build and plan modes, plus a desktop app213.5k starsMIT	79 out of 100
3	piTerminal coding agent with extensions, skills, and an SDK115.2k starsMIT	79 out of 100
#4	orcaDesktop app that runs CLI coding agents in parallel git worktrees92.5k starsMIT	78 out of 100
#5	oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory70k starscustom license	78 out of 100

How to choose

Check which models it can use: your own keys, local models, or only the vendor's.
See what it may do without asking (edit files, run shell, push) and how you approve.
Prefer agents that work in a branch or worktree you can throw away.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

MIT Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the copyright and license notice in copies you ship.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#40 of 52 in Coding agents and assistants on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/frankbria/ralph-claude-code.svg)](https://archestack.com/best-of-vibe-coding/projects/ralph-claude-code/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-vibe-coding/ralph-claude-code/" title="ralph-claude-code on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Vibe Coding on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with ralph-claude-code filled in.