Ralph Wiggum Loop
Autonomous iterative AI development MCP server with spec-driven worker/reviewer SHIP/REVISE loops.
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
https://github.com/sheldonrobinson/ralph-wiggum-loop/releases/download/v1.1.0/ralph-wiggum-loop.sh.mcpbclaude mcp add ralph-wiggum-loop -e 'RALPH_STATE_BASE=<RALPH_STATE_BASE>' -e 'RALPH_RECIPE_DIR=<RALPH_RECIPE_DIR>' -- sh --stdio
{
"mcpServers": {
"ralph-wiggum-loop": {
"command": "sh",
"args": [
"--stdio"
],
"env": {
"RALPH_STATE_BASE": "<RALPH_STATE_BASE>",
"RALPH_RECIPE_DIR": "<RALPH_RECIPE_DIR>"
}
}
}
}
Variables d'environnement
RALPH_STATE_BASEDirectory path where active Ralph Loop state and iteration history are storedRALPH_RECIPE_DIRDirectory path containing workflow recipe JSON files
https://github.com/sheldonrobinson/ralph-wiggum-loop/releases/download/v1.1.0/ralph-wiggum-loop.pwsh.mcpbclaude mcp add ralph-wiggum-loop -e 'RALPH_STATE_BASE=<RALPH_STATE_BASE>' -e 'RALPH_RECIPE_DIR=<RALPH_RECIPE_DIR>' -- pwsh -Stdio
{
"mcpServers": {
"ralph-wiggum-loop": {
"command": "pwsh",
"args": [
"-Stdio"
],
"env": {
"RALPH_STATE_BASE": "<RALPH_STATE_BASE>",
"RALPH_RECIPE_DIR": "<RALPH_RECIPE_DIR>"
}
}
}
}
Variables d'environnement
RALPH_STATE_BASEDirectory path where active Ralph Loop state and iteration history are storedRALPH_RECIPE_DIRDirectory path containing workflow recipe JSON files
Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
Sommaire
ralph-wiggum-loop
Multi-model iterative development agent plugin — Ralph Loop with cross-model worker/reviewer architecture, spec-driven development skills, Stop hooks, and SHIP/REVISE decision engine.
Overview
The Ralph Loop implements a two-phase iterative workflow where a worker model does the work and a reviewer model provides cross-model review, iterating until the reviewer says "SHIP".
This project is a cross-platform Agent Plugin (plugin.json, mcp.json, .agents/skills/ralph-wiggum-loop/ & skills/ralph-wiggum-loop/) with native implementations for:
- Linux / macOS (Bash):
bin/ralph-wiggum-loop.sh(usingbin/mcp-sdk.sh) - Windows (PowerShell):
bin/ralph-wiggum-loop.ps1(usingbin/mcp-sdk.psm1) - Polyglot Runner:
bin/script-runner.sh/bin/script-runner.ps1(runs in both POSIXsh/bashand PowerShell)
Install Skill (.agents/skills/)
Per the Agent Skills Specification, install the skill to .agents/skills/:
# Project-level (.agents/skills/ralph-wiggum-loop) or User-level (~/.agents/skills/ralph-wiggum-loop)
mkdir -p .agents/skills
cp -R skills/ralph-wiggum-loop .agents/skills/ralph-wiggum-loop
New-Item -ItemType Directory -Path .agents/skills -Force | Out-Null
Copy-Item -Recurse -Force skills/ralph-wiggum-loop .agents/skills/ralph-wiggum-loop
OS-Specific MCP Servers (mcp.json)
| MCP Server Name | OS / Runtime | Transport | Command / Endpoint |
|---|---|---|---|
ralph-wiggum-loop | Linux / macOS (Bash) | stdio | ./bin/script-runner.sh ralph-wiggum-loop --stdio |
ralph-wiggum-loop-pwsh | Windows (PowerShell 7+) | stdio | pwsh -NoProfile -ExecutionPolicy Bypass -File ${PLUGIN_ROOT}/bin/script-runner.ps1 ralph-wiggum-loop --stdio |
ralph-wiggum-loop-powershell | Windows (PowerShell 5.1) | stdio | powershell.exe -NoProfile -ExecutionPolicy Bypass -File ${PLUGIN_ROOT}/bin/script-runner.ps1 ralph-wiggum-loop --stdio |
ralph-wiggum-loop-http | Cross-Platform | streamable-http | http://127.0.0.1:8080/mcp |
Quick Start
1. CLI Mode
- Linux / macOS (Bash):
./bin/ralph-wiggum-loop.sh "Implement user authentication with JWT tokens" --profile pro - Windows (PowerShell):
pwsh -NoProfile -ExecutionPolicy Bypass -File .\bin\ralph-wiggum-loop.ps1 "Implement user authentication with JWT tokens" --profile pro
2. MCP Server (stdio Mode)
- Linux / macOS (Bash):
./bin/ralph-wiggum-loop.sh --stdio - Windows (PowerShell):
pwsh -NoProfile -ExecutionPolicy Bypass -File .\bin\ralph-wiggum-loop.ps1 --stdio
3. MCP Server (streamable-http Service Mode)
- Linux / macOS (Bash):
./bin/script-runner.sh start-http-server start --host 127.0.0.1 --port 8080 - Windows (PowerShell):
pwsh -NoProfile -ExecutionPolicy Bypass -File .\bin\script-runner.ps1 start-http-server start --host 127.0.0.1 --port 8080
Documentation
- Skill & Agent Instructions — OS selection rules, loop execution modes, and Streamable HTTP setup
- Full Documentation — API reference, tools, state management
- Deployment Guide — Install and configure
Repository
- Source: https://github.com/sheldonrobinson/ralph-wiggum-loop
- Agent Plugin Spec: https://agent-plugins.org
- MCP Spec: https://modelcontextprotocol.io
License
MIT
Questions fréquentes
Qu'est-ce que Ralph Wiggum Loop ?
Autonomous iterative AI development MCP server with spec-driven worker/reviewer SHIP/REVISE loops.
Comment installer Ralph Wiggum Loop ?
Il s'exécute sur votre machine. Dans Claude Code : claude mcp add ralph-wiggum-loop -e 'RALPH_STATE_BASE=<RALPH_STATE_BASE>' -e 'RALPH_RECIPE_DIR=<RALPH_RECIPE_DIR>' -- sh --stdio. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour Ralph Wiggum Loop ?
Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.
Ralph Wiggum Loop est-il open source ?
Oui. Son code est sur GitHub sous licence MIT.
Qui maintient Ralph Wiggum Loop ?
Il est publié par sheldonrobinson. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.