You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Category: Official Documentation
Sub-category: General
Author: Anthropic PBC
From issue: #454
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Copy file name to clipboardExpand all lines: README.md
+2-1Lines changed: 2 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -31,9 +31,9 @@ Claude Code is a CLI-based coding assistant from [Anthropic](https://www.anthrop
31
31
32
32
## Latest Additions
33
33
34
+
-[Ralph Wiggum Plugin](https://github.com/anthropics/claude-code/tree/4f18698a9ed25517861a75125b526e319bcf8354/plugins/ralph-wiggum) by [Anthropic PBC](https://github.com/anthropics) - The official Anthropic implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code.
34
35
-[ralph-orchestrator](https://github.com/mikeyobrien/ralph-orchestrator) by [mikeyobrien](https://github.com/mikeyobrien) - Ralph Orchestrator implements the simple but effective "Ralph Wiggum" technique for autonomous task completion, continuously running an AI agent against a prompt file until the task is marked as complete or limits are reached. This implementation provides a robust, well-tested, and feature-complete orchestration system for AI-driven development. Also cited in the Anthropic Ralph plugin documentation.
35
36
-[Ralph for Claude Code](https://github.com/frankbria/ralph-claude-code) by [Frank Bria](https://github.com/frankbria) - An autonomous AI development framework that enables Claude Code to work iteratively on projects until completion. Features intelligent exit detection, rate limiting, circuit breaker patterns, and comprehensive safety guardrails to prevent infinite loops and API overuse. Built with Bash, integrated with tmux for live monitoring, and includes 75+ comprehensive tests.
36
-
-[Claude Code Repos Index](https://github.com/danielrosehill/Claude-Code-Repos-Index) by [Daniel Rosehill](https://github.com/danielrosehill) - This is either the work of a prolific genius, or a very clever bot (or both), although it hardly matters because the quality is so good - an index of 75+ Claude Code repositories published by the author - and I'm not talking about slop. CMS, system design, deep research, IoT, agentic workflows, server management, personal health... If you spot the lie, let me know, otherwise please check these out.
37
37
38
38
39
39
## Contents
@@ -345,6 +345,7 @@ Claude Code is a CLI-based coding assistant from [Anthropic](https://www.anthrop
345
345
-[Anthropic Documentation](https://docs.claude.com/en/home) by [Anthropic](https://github.com/anthropics) - The official documentation for Claude Code, including installation instructions, usage guidelines, API references, tutorials, examples, loads of information that I won't list individually. Like Claude Code, the documentation is frequently updated.
346
346
-[Anthropic Quickstarts](https://github.com/anthropics/claude-quickstarts) by [Anthropic](https://github.com/anthropics) - Offers comprehensive development guides for three distinct AI-powered demo projects with standardized workflows, strict code style guidelines, and containerization instructions.
347
347
-[Claude Code GitHub Actions](https://github.com/anthropics/claude-code-action/tree/main/examples) by [Anthropic](https://github.com/anthropics) - Official GitHub Actions integration for Claude Code with examples and documentation for automating AI-powered workflows in CI/CD pipelines.
348
+
-[Ralph Wiggum Plugin](https://github.com/anthropics/claude-code/tree/4f18698a9ed25517861a75125b526e319bcf8354/plugins/ralph-wiggum) by [Anthropic PBC](https://github.com/anthropics) - The official Anthropic implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code.
Copy file name to clipboardExpand all lines: README_ALTERNATIVES/README_AWESOME.md
+2-1Lines changed: 2 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -31,9 +31,9 @@ Claude Code is a CLI-based coding assistant from [Anthropic](https://www.anthrop
31
31
32
32
## Latest Additions
33
33
34
+
-[Ralph Wiggum Plugin](https://github.com/anthropics/claude-code/tree/4f18698a9ed25517861a75125b526e319bcf8354/plugins/ralph-wiggum) by [Anthropic PBC](https://github.com/anthropics) - The official Anthropic implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code.
34
35
-[ralph-orchestrator](https://github.com/mikeyobrien/ralph-orchestrator) by [mikeyobrien](https://github.com/mikeyobrien) - Ralph Orchestrator implements the simple but effective "Ralph Wiggum" technique for autonomous task completion, continuously running an AI agent against a prompt file until the task is marked as complete or limits are reached. This implementation provides a robust, well-tested, and feature-complete orchestration system for AI-driven development. Also cited in the Anthropic Ralph plugin documentation.
35
36
-[Ralph for Claude Code](https://github.com/frankbria/ralph-claude-code) by [Frank Bria](https://github.com/frankbria) - An autonomous AI development framework that enables Claude Code to work iteratively on projects until completion. Features intelligent exit detection, rate limiting, circuit breaker patterns, and comprehensive safety guardrails to prevent infinite loops and API overuse. Built with Bash, integrated with tmux for live monitoring, and includes 75+ comprehensive tests.
36
-
-[Claude Code Repos Index](https://github.com/danielrosehill/Claude-Code-Repos-Index) by [Daniel Rosehill](https://github.com/danielrosehill) - This is either the work of a prolific genius, or a very clever bot (or both), although it hardly matters because the quality is so good - an index of 75+ Claude Code repositories published by the author - and I'm not talking about slop. CMS, system design, deep research, IoT, agentic workflows, server management, personal health... If you spot the lie, let me know, otherwise please check these out.
37
37
38
38
39
39
## Contents
@@ -345,6 +345,7 @@ Claude Code is a CLI-based coding assistant from [Anthropic](https://www.anthrop
345
345
-[Anthropic Documentation](https://docs.claude.com/en/home) by [Anthropic](https://github.com/anthropics) - The official documentation for Claude Code, including installation instructions, usage guidelines, API references, tutorials, examples, loads of information that I won't list individually. Like Claude Code, the documentation is frequently updated.
346
346
-[Anthropic Quickstarts](https://github.com/anthropics/claude-quickstarts) by [Anthropic](https://github.com/anthropics) - Offers comprehensive development guides for three distinct AI-powered demo projects with standardized workflows, strict code style guidelines, and containerization instructions.
347
347
-[Claude Code GitHub Actions](https://github.com/anthropics/claude-code-action/tree/main/examples) by [Anthropic](https://github.com/anthropics) - Official GitHub Actions integration for Claude Code with examples and documentation for automating AI-powered workflows in CI/CD pipelines.
348
+
-[Ralph Wiggum Plugin](https://github.com/anthropics/claude-code/tree/4f18698a9ed25517861a75125b526e319bcf8354/plugins/ralph-wiggum) by [Anthropic PBC](https://github.com/anthropics) - The official Anthropic implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code.
Copy file name to clipboardExpand all lines: README_ALTERNATIVES/README_CLASSIC.md
+20-9Lines changed: 20 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -46,35 +46,35 @@ Claude Code is a cutting-edge CLI-based coding assistant and agent released by [
46
46
## Latest Additions ✨ [🔝](#awesome-claude-code)
47
47
48
48
49
-
[`ralph-orchestrator`](https://github.com/mikeyobrien/ralph-orchestrator) by [mikeyobrien](https://github.com/mikeyobrien) ⚖️ MIT
50
-
Ralph Orchestrator implements the simple but effective "Ralph Wiggum" technique for autonomous task completion, continuously running an AI agent against a prompt file until the task is marked as complete or limits are reached. This implementation provides a robust, well-tested, and feature-complete orchestration system for AI-driven development. Also cited in the Anthropic Ralph plugin documentation.
The official Anthropic implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code.
51
51
52
52
<details>
53
53
<summary>📊 GitHub Stats</summary>
54
54
55
-

55
+

56
56
57
57
</details>
58
58
<br>
59
59
60
-
[`Ralph for Claude Code`](https://github.com/frankbria/ralph-claude-code) by [Frank Bria](https://github.com/frankbria) ⚖️ MIT
61
-
An autonomous AI development framework that enables Claude Code to work iteratively on projects until completion. Features intelligent exit detection, rate limiting, circuit breaker patterns, and comprehensive safety guardrails to prevent infinite loops and API overuse. Built with Bash, integrated with tmux for live monitoring, and includes 75+ comprehensive tests.
60
+
[`ralph-orchestrator`](https://github.com/mikeyobrien/ralph-orchestrator) by [mikeyobrien](https://github.com/mikeyobrien) ⚖️ MIT
61
+
Ralph Orchestrator implements the simple but effective "Ralph Wiggum" technique for autonomous task completion, continuously running an AI agent against a prompt file until the task is marked as complete or limits are reached. This implementation provides a robust, well-tested, and feature-complete orchestration system for AI-driven development. Also cited in the Anthropic Ralph plugin documentation.
62
62
63
63
<details>
64
64
<summary>📊 GitHub Stats</summary>
65
65
66
-

66
+

67
67
68
68
</details>
69
69
<br>
70
70
71
-
[`Claude Code Repos Index`](https://github.com/danielrosehill/Claude-Code-Repos-Index) by [Daniel Rosehill](https://github.com/danielrosehill)
72
-
This is either the work of a prolific genius, or a very clever bot (or both), although it hardly matters because the quality is so good - an index of 75+ Claude Code repositories published by the author - and I'm not talking about slop. CMS, system design, deep research, IoT, agentic workflows, server management, personal health... If you spot the lie, let me know, otherwise please check these out.
71
+
[`Ralph for Claude Code`](https://github.com/frankbria/ralph-claude-code) by [Frank Bria](https://github.com/frankbria) ⚖️ MIT
72
+
An autonomous AI development framework that enables Claude Code to work iteratively on projects until completion. Features intelligent exit detection, rate limiting, circuit breaker patterns, and comprehensive safety guardrails to prevent infinite loops and API overuse. Built with Bash, integrated with tmux for live monitoring, and includes 75+ comprehensive tests.
73
73
74
74
<details>
75
75
<summary>📊 GitHub Stats</summary>
76
76
77
-

77
+

78
78
79
79
</details>
80
80
<br>
@@ -2076,6 +2076,17 @@ Official GitHub Actions integration for Claude Code with examples and documentat
The official Anthropic implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code.
2081
+
2082
+
<details>
2083
+
<summary>📊 GitHub Stats</summary>
2084
+
2085
+

_The official Anthropic implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code._
192
+

_Ralph Orchestrator implements the simple but effective "Ralph Wiggum" technique for autonomous task completion, continuously running an AI agent against a prompt file until the task is marked as complete or limits are reached. This implementation provides a robust, well-tested, and feature-complete orchestration system for AI-driven development. Also cited in the Anthropic Ralph plugin documentation._
192
196

@@ -195,10 +199,6 @@ _Ralph Orchestrator implements the simple but effective "Ralph Wiggum" technique
195
199
_An autonomous AI development framework that enables Claude Code to work iteratively on projects until completion. Features intelligent exit detection, rate limiting, circuit breaker patterns, and comprehensive safety guardrails to prevent infinite loops and API overuse. Built with Bash, integrated with tmux for live monitoring, and includes 75+ comprehensive tests._
196
200

_This is either the work of a prolific genius, or a very clever bot (or both), although it hardly matters because the quality is so good - an index of 75+ Claude Code repositories published by the author - and I'm not talking about slop. CMS, system design, deep research, IoT, agentic workflows, server management, personal health... If you spot the lie, let me know, otherwise please check these out._
200
-

201
-
202
202
203
203
<br>
204
204
@@ -2060,6 +2060,13 @@ _Official GitHub Actions integration for Claude Code with examples and documenta
_The official Anthropic implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code._
2065
+

0 commit comments