pi-orchestration
Orchestrate multiple AI models (GLM, MiniMax, etc.) as workers using Pi Coding Agent with Claude as coordinator.
When & Why to Use This Skill
The Pi Orchestration skill empowers Claude to act as a central coordinator for multi-model AI workflows. By leveraging the Pi Coding Agent, it allows users to spawn and manage multiple AI models (including GLM, MiniMax, OpenAI, and Anthropic) as background workers. This skill is ideal for executing complex, parallelized tasks such as map-reduce patterns, multi-file code reviews, and distributed content generation, significantly enhancing the efficiency of AI-driven development and automation.
Use Cases
- Parallel Code Review: Dispatch multiple AI workers to simultaneously analyze different files for security vulnerabilities, performance bottlenecks, and logic errors, then aggregate the findings.
- Map-Reduce Data Processing: Break down large-scale data tasks into smaller chunks, process them in parallel using background worker sessions (via tmux), and collect the results into a single report.
- Multi-Model Task Optimization: Assign sub-tasks to specific models based on their strengths, such as using GLM for high-quality Chinese language processing and MiniMax for creative content generation.
- Automated Feature Building: Orchestrate background workers to build independent components of a software project while the lead agent maintains the high-level architecture and project state.
| name | pi-orchestration |
|---|---|
| description | Orchestrate multiple AI models (GLM, MiniMax, etc.) as workers using Pi Coding Agent with Claude as coordinator. |
| homepage | https://github.com/mariozechner/pi-coding-agent |
| metadata | {"clawdis":{"emoji":"🎭","requires":{"bins":["pi"]}}} |
Pi Orchestration
Use Claude as an orchestrator to spawn and coordinate multiple AI model workers (GLM, MiniMax, etc.) via Pi Coding Agent.
Supported Providers
| Provider | Model | Status |
|---|---|---|
| GLM | glm-4.7 | ✅ Working |
| MiniMax | MiniMax-M2.1 | ✅ Working |
| OpenAI | gpt-4o, etc. | ✅ Working |
| Anthropic | claude-* | ✅ Working |
Setup
1. GLM (Zhipu AI)
Get API key from open.bigmodel.cn
export GLM_API_KEY="your-glm-api-key"
2. MiniMax
Get API key from api.minimax.chat
export MINIMAX_API_KEY="your-minimax-api-key"
export MINIMAX_GROUP_ID="your-group-id" # Required for MiniMax
Usage
Direct Commands
# GLM-4.7
pi --provider glm --model glm-4.7 -p "Your task"
# MiniMax M2.1
pi --provider minimax --model MiniMax-M2.1 -p "Your task"
# Test connectivity
pi --provider glm --model glm-4.7 -p "Say hello"
Orchestration Patterns
Claude (Opus) can spawn these as background workers:
Background Worker
bash workdir:/tmp/task background:true command:"pi --provider glm --model glm-4.7 -p 'Build feature X'"
Parallel Army (tmux)
# Create worker sessions
tmux new-session -d -s worker-1
tmux new-session -d -s worker-2
# Dispatch tasks
tmux send-keys -t worker-1 "pi --provider glm --model glm-4.7 -p 'Task 1'" Enter
tmux send-keys -t worker-2 "pi --provider minimax --model MiniMax-M2.1 -p 'Task 2'" Enter
# Check progress
tmux capture-pane -t worker-1 -p
tmux capture-pane -t worker-2 -p
Map-Reduce Pattern
# Map: Distribute subtasks to workers
for i in 1 2 3; do
tmux send-keys -t worker-$i "pi --provider glm --model glm-4.7 -p 'Process chunk $i'" Enter
done
# Reduce: Collect and combine results
for i in 1 2 3; do
tmux capture-pane -t worker-$i -p >> /tmp/results.txt
done
Orchestration Script
# Quick orchestration helper
uv run {baseDir}/scripts/orchestrate.py spawn --provider glm --model glm-4.7 --task "Build a REST API"
uv run {baseDir}/scripts/orchestrate.py status
uv run {baseDir}/scripts/orchestrate.py collect
Best Practices
- Task Decomposition: Break large tasks into independent subtasks
- Model Selection: Use GLM for Chinese content, MiniMax for creative tasks
- Error Handling: Check worker status before collecting results
- Resource Management: Clean up tmux sessions after completion
Example: Parallel Code Review
# Claude orchestrates 3 workers to review different files
tmux send-keys -t worker-1 "pi --provider glm -p 'Review auth.py for security issues'" Enter
tmux send-keys -t worker-2 "pi --provider minimax -p 'Review api.py for performance'" Enter
tmux send-keys -t worker-3 "pi --provider glm -p 'Review db.py for SQL injection'" Enter
# Wait and collect
sleep 30
for i in 1 2 3; do
echo "=== Worker $i ===" >> review.md
tmux capture-pane -t worker-$i -p >> review.md
done
Notes
- Pi Coding Agent must be installed:
npm install -g @anthropic/pi-coding-agent - GLM and MiniMax have generous free tiers
- Claude acts as coordinator, workers do the heavy lifting
- Combine with process tool for background task management