Add Ralph CLI section to README.md
Changes: - Update "What's Included": Add Ralph CLI Integration (Advanced) - Add comprehensive "Ralph CLI Integration" section: * What Ralph CLI does * How it works (background execution) * Key features table * Control modes (agents/always/off) * Monitoring & control commands * Real-life example workflow * Ralph vs PROACTIVELY comparison table * Installation instructions * When to use Ralph CLI - Update "Complete Source Guide": 6 → 7 major open-source projects - Add Ralph CLI as 6th component in source guide Total Ralph mentions: 0 → 37 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
161
README.md
161
README.md
@@ -175,6 +175,7 @@ Follow the step-by-step guide below for full control over each component.
|
|||||||
- **7 PROACTIVELY coordinators** that auto-trigger and orchestrate specialists
|
- **7 PROACTIVELY coordinators** that auto-trigger and orchestrate specialists
|
||||||
- **31 specialist agents** for domain-specific tasks
|
- **31 specialist agents** for domain-specific tasks
|
||||||
- **🔧 15+ MCP Tools** for vision, search, and GitHub integration
|
- **🔧 15+ MCP Tools** for vision, search, and GitHub integration
|
||||||
|
- **🤖 Ralph CLI Integration** (Advanced) - Autonomous agent looping with background execution
|
||||||
- **⚡ Intelligent Coordination** - Coordinators automatically detect context and orchestrate workflows
|
- **⚡ Intelligent Coordination** - Coordinators automatically detect context and orchestrate workflows
|
||||||
- **🎛️ Interactive Installation** with model selection (Anthropic/Z.AI)
|
- **🎛️ Interactive Installation** with model selection (Anthropic/Z.AI)
|
||||||
- **🛡️ One-Click Setup** with comprehensive verification
|
- **🛡️ One-Click Setup** with comprehensive verification
|
||||||
@@ -364,6 +365,155 @@ Result: Complete viral app, launch-ready, in 2 weeks ✓
|
|||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
|
## 🤖 Ralph CLI Integration (Advanced)
|
||||||
|
|
||||||
|
**🔗 Source:** [@iannuttall/ralph](https://github.com/iannuttall/ralph)
|
||||||
|
|
||||||
|
> **⚠️ Advanced Feature:** Ralph CLI provides autonomous agent looping for complex, multi-hour development sessions. It's optional but powerful for "fire and forget" workflows.
|
||||||
|
|
||||||
|
### What Ralph CLI Does
|
||||||
|
|
||||||
|
**PROACTIVELY Agents** = Quick coordination (single interaction)
|
||||||
|
**Ralph CLI** = Autonomous looping (multi-iteration, background execution)
|
||||||
|
|
||||||
|
Ralph CLI runs in the **background** (non-blocking), allowing you to continue working in Claude Code while it autonomously completes complex tasks.
|
||||||
|
|
||||||
|
### How It Works
|
||||||
|
|
||||||
|
```
|
||||||
|
1. You request: "Build a TikTok app in 2 weeks"
|
||||||
|
↓
|
||||||
|
2. Hook detects agent request
|
||||||
|
↓
|
||||||
|
3. Hook spawns Ralph in BACKGROUND (non-blocking)
|
||||||
|
↓
|
||||||
|
4. Claude Code immediately continues ← You keep working!
|
||||||
|
↓
|
||||||
|
5. Ralph autonomously loops in background:
|
||||||
|
- Iteration 1: rapid-prototyper builds MVP
|
||||||
|
- Iteration 2: tiktok-strategist plans viral features
|
||||||
|
- Iteration 3: frontend-developer builds UI
|
||||||
|
- Continues until complete or max iterations reached
|
||||||
|
↓
|
||||||
|
6. Monitor Ralph: tail -f ~/.claude/ralph-output.log
|
||||||
|
```
|
||||||
|
|
||||||
|
### Key Features
|
||||||
|
|
||||||
|
| Feature | Description |
|
||||||
|
|---------|-------------|
|
||||||
|
| **Background Execution** | Runs as background process (NON-BLOCKING) |
|
||||||
|
| **Auto-Spawning** | Hook automatically starts Ralph when needed |
|
||||||
|
| **Process Tracking** | PID file for monitoring and control |
|
||||||
|
| **Lock Mechanism** | Prevents duplicate Ralph instances |
|
||||||
|
| **Real-time Logging** | Monitor progress: `tail -f ~/.claude/ralph-output.log` |
|
||||||
|
| **Persistent State** | State preserved in `~/.claude/ralph-loop.local.md` |
|
||||||
|
|
||||||
|
### Control Modes
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Mode 1: Auto-start only for agent requests (default)
|
||||||
|
export RALPH_AUTO_MODE="agents"
|
||||||
|
|
||||||
|
# Mode 2: Auto-start for everything
|
||||||
|
export RALPH_AUTO_MODE="always"
|
||||||
|
|
||||||
|
# Mode 3: Disable auto-start
|
||||||
|
export RALPH_AUTO_MODE="off"
|
||||||
|
|
||||||
|
# Set max iterations (default: 50)
|
||||||
|
export RALPH_MAX_ITERATIONS="100"
|
||||||
|
```
|
||||||
|
|
||||||
|
### Monitoring & Control
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Monitor Ralph's output in real-time
|
||||||
|
tail -f ~/.claude/ralph-output.log
|
||||||
|
|
||||||
|
# Check if Ralph is running
|
||||||
|
cat ~/.claude/ralph.pid
|
||||||
|
|
||||||
|
# Stop Ralph manually
|
||||||
|
kill $(cat ~/.claude/ralph.pid)
|
||||||
|
rm ~/.claude/ralph.lock
|
||||||
|
|
||||||
|
# View trigger history
|
||||||
|
cat ~/.claude/ralph-trigger.log
|
||||||
|
```
|
||||||
|
|
||||||
|
### Real-Life Example
|
||||||
|
|
||||||
|
**Scenario:** You need to build a complex feature while handling other tasks.
|
||||||
|
|
||||||
|
```bash
|
||||||
|
You: "Use the ai-engineer to implement a machine learning pipeline"
|
||||||
|
|
||||||
|
[Hook triggers automatically]
|
||||||
|
|
||||||
|
🔄 Ralph CLI auto-started in background
|
||||||
|
PID: 12345
|
||||||
|
Agent: ai-engineer
|
||||||
|
Monitor: tail -f ~/.claude/ralph-output.log
|
||||||
|
|
||||||
|
Claude: "I've delegated the ML pipeline to Ralph, which is now
|
||||||
|
working autonomously in the background (20-30 min expected).
|
||||||
|
I'm still available to help with other tasks!"
|
||||||
|
|
||||||
|
You: "Perfect. While Ralph works on the ML pipeline, can you help me
|
||||||
|
write unit tests for the authentication module?"
|
||||||
|
|
||||||
|
Claude: "Absolutely! Let's write those tests..."
|
||||||
|
[You work on tests while Ralph builds the ML pipeline in background]
|
||||||
|
```
|
||||||
|
|
||||||
|
### Ralph vs PROACTIVELY Agents
|
||||||
|
|
||||||
|
| Feature | Ralph CLI (Background) | PROACTIVELY Agents |
|
||||||
|
|---------|------------------------|-------------------|
|
||||||
|
| **Execution** | Multi-loop, background | Single interaction |
|
||||||
|
| **Blocking** | NON-BLOCKING | Blocking (waits) |
|
||||||
|
| **State** | File + log | Context only |
|
||||||
|
| **Control** | Manual stop (PID) | Automatic completion |
|
||||||
|
| **Best For** | Large projects, overnight | Quick tasks, collaboration |
|
||||||
|
|
||||||
|
### Installation
|
||||||
|
|
||||||
|
Ralph CLI is available as an **optional** installation step in both:
|
||||||
|
- **MASTER-PROMPT.md** (Step 6)
|
||||||
|
- **interactive-install-claude.sh** (Step 6: Ralph CLI Selection)
|
||||||
|
|
||||||
|
**To install:**
|
||||||
|
```bash
|
||||||
|
npm install -g @iannuttall/ralph
|
||||||
|
```
|
||||||
|
|
||||||
|
**To enable auto-trigger:**
|
||||||
|
```bash
|
||||||
|
# The installer creates the hook automatically
|
||||||
|
# Or manually: Follow Step 6 in MASTER-PROMPT.md
|
||||||
|
```
|
||||||
|
|
||||||
|
### When to Use Ralph CLI
|
||||||
|
|
||||||
|
✅ **Use Ralph CLI for:**
|
||||||
|
- Complex multi-step projects (2+ hours)
|
||||||
|
- "Fire and forget" autonomous coding
|
||||||
|
- Overnight builds/refactors
|
||||||
|
- Large-scale refactoring
|
||||||
|
- Multi-feature implementations
|
||||||
|
|
||||||
|
❌ **Use PROACTIVELY agents for:**
|
||||||
|
- Quick tasks (minutes)
|
||||||
|
- Human collaboration needed
|
||||||
|
- Design discussions
|
||||||
|
- Code reviews
|
||||||
|
- Quick fixes
|
||||||
|
|
||||||
|
**You can use BOTH together** - Set `RALPH_AUTO_MODE="agents"` for a hybrid approach where Ralph assists with big tasks while PROACTIVELY agents handle quick coordination.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
## 🔧 MCP Tools
|
## 🔧 MCP Tools
|
||||||
|
|
||||||
### Vision Tools (8 tools)
|
### Vision Tools (8 tools)
|
||||||
@@ -400,11 +550,11 @@ Result: Complete viral app, launch-ready, in 2 weeks ✓
|
|||||||
|
|
||||||
## 📖 Complete Source Guide
|
## 📖 Complete Source Guide
|
||||||
|
|
||||||
This suite integrates **6 major open-source projects**:
|
This suite integrates **7 major open-source projects**:
|
||||||
|
|
||||||
### 1. contains-studio/agents 🎭
|
### 1. contains-studio/agents 🎭
|
||||||
**Source:** https://github.com/contains-studio/agents
|
**Source:** https://github.com/contains-studio/agents
|
||||||
**Provides:** 37 specialized agents with PROACTIVELY auto-triggering
|
**Provides:** 38 specialized agents with PROACTIVELY auto-triggering
|
||||||
**Key Innovation:** Context-aware agent selection system
|
**Key Innovation:** Context-aware agent selection system
|
||||||
|
|
||||||
### 2. @z_ai/mcp-server 🖼️
|
### 2. @z_ai/mcp-server 🖼️
|
||||||
@@ -427,7 +577,12 @@ This suite integrates **6 major open-source projects**:
|
|||||||
**Provides:** Professional UI/UX design agent with comprehensive patterns
|
**Provides:** Professional UI/UX design agent with comprehensive patterns
|
||||||
**Key Feature:** PROACTIVELY auto-triggering for all design work
|
**Key Feature:** PROACTIVELY auto-triggering for all design work
|
||||||
|
|
||||||
### 6. claude-codex-settings 📋
|
### 6. @iannuttall/ralph 🤖
|
||||||
|
**Source:** https://github.com/iannuttall/ralph
|
||||||
|
**Provides:** Autonomous agent looping with background execution
|
||||||
|
**Key Feature:** "Fire and forget" multi-iteration development
|
||||||
|
|
||||||
|
### 7. claude-codex-settings 📋
|
||||||
**Source:** https://github.com/fcakyon/claude-codex-settings
|
**Source:** https://github.com/fcakyon/claude-codex-settings
|
||||||
**Provides:** MCP configuration best practices (reference)
|
**Provides:** MCP configuration best practices (reference)
|
||||||
**Key Feature:** Proven integration patterns
|
**Key Feature:** Proven integration patterns
|
||||||
|
|||||||
Reference in New Issue
Block a user