6.8 KiB

Raw Blame History

CLI Multi-Agent Features: 3-Step Quickstart Guide

Run LLM Council and Heavy Swarm directly from the command line for seamless DevOps integration. Execute sophisticated multi-agent workflows without writing Python code.

Overview

Feature	Description
LLM Council CLI	Run collaborative decision-making from terminal
Heavy Swarm CLI	Execute comprehensive research swarms
DevOps Ready	Integrate into CI/CD pipelines and scripts
Configurable	Full parameter control from command line

Step 1: Install and Verify

Ensure Swarms is installed and verify CLI access:

# Install swarms
pip install swarms

# Verify CLI is available
swarms --help

You should see the Swarms CLI banner and available commands.

Step 2: Set Environment Variables

Configure your API keys:

# Set your OpenAI API key (or other provider)
export OPENAI_API_KEY="your-openai-api-key"

# Optional: Set workspace directory
export WORKSPACE_DIR="./agent_workspace"

Or add to your .env file:

OPENAI_API_KEY=your-openai-api-key
WORKSPACE_DIR=./agent_workspace

Step 3: Run Multi-Agent Commands

LLM Council

Run a collaborative council of AI agents:

# Basic usage
swarms llm-council --task "What is the best approach to implement microservices architecture?"

# With verbose output
swarms llm-council --task "Evaluate investment opportunities in AI startups" --verbose

Heavy Swarm

Run comprehensive research and analysis:

# Basic usage
swarms heavy-swarm --task "Analyze the current state of quantum computing"

# With configuration options
swarms heavy-swarm \
    --task "Research renewable energy market trends" \
    --loops-per-agent 2 \
    --question-agent-model-name gpt-4o-mini \
    --worker-model-name gpt-4o-mini \
    --verbose

Complete CLI Reference

LLM Council Command

swarms llm-council --task "<your query>" [options]

Option	Description
`--task`	Required. The query or question for the council
`--verbose`	Enable detailed output logging

Examples:

# Strategic decision
swarms llm-council --task "Should our startup pivot from B2B to B2C?"

# Technical evaluation
swarms llm-council --task "Compare React vs Vue for enterprise applications"

# Business analysis
swarms llm-council --task "What are the risks of expanding to European markets?"

Heavy Swarm Command

swarms heavy-swarm --task "<your task>" [options]

Option	Default	Description
`--task`	-	Required. The research task
`--loops-per-agent`	1	Number of loops per agent
`--question-agent-model-name`	gpt-4o-mini	Model for question agent
`--worker-model-name`	gpt-4o-mini	Model for worker agents
`--random-loops-per-agent`	False	Randomize loops per agent
`--verbose`	False	Enable detailed output

Examples:

# Comprehensive research
swarms heavy-swarm --task "Research the impact of AI on healthcare diagnostics" --verbose

# With custom models
swarms heavy-swarm \
    --task "Analyze cryptocurrency regulation trends globally" \
    --question-agent-model-name gpt-4 \
    --worker-model-name gpt-4 \
    --loops-per-agent 3

# Quick analysis
swarms heavy-swarm --task "Summarize recent advances in battery technology"

Integration Examples

Bash Script Integration

#!/bin/bash
# research_script.sh

TOPICS=(
    "AI in manufacturing"
    "Autonomous vehicles market"
    "Edge computing trends"
)

for topic in "${TOPICS[@]}"; do
    echo "Researching: $topic"
    swarms heavy-swarm --task "Analyze $topic" --verbose >> research_output.txt
    echo "---" >> research_output.txt
done

CI/CD Pipeline (GitHub Actions)

name: AI Research Pipeline

on:
  schedule:
    - cron: '0 9 * * 1'  # Every Monday at 9 AM

jobs:
  research:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      
      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: '3.10'
      
      - name: Install dependencies
        run: pip install swarms
      
      - name: Run LLM Council
        env:
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
        run: |
          swarms llm-council \
            --task "Weekly market analysis for tech sector" \
            --verbose > weekly_analysis.txt          
      
      - name: Upload results
        uses: actions/upload-artifact@v3
        with:
          name: analysis-results
          path: weekly_analysis.txt

Docker Integration

FROM python:3.10-slim

RUN pip install swarms

ENV OPENAI_API_KEY=""
ENV WORKSPACE_DIR="/workspace"

WORKDIR /workspace

ENTRYPOINT ["swarms"]
CMD ["--help"]

# Build and run
docker build -t swarms-cli .
docker run -e OPENAI_API_KEY="your-key" swarms-cli \
    llm-council --task "Analyze market trends"

Other Useful CLI Commands

Setup Check

Verify your environment is properly configured:

swarms setup-check --verbose

Run Single Agent

Execute a single agent task:

swarms agent \
    --name "Research-Agent" \
    --task "Summarize recent AI developments" \
    --model "gpt-4o-mini" \
    --max-loops 1

Auto Swarm

Automatically generate and run a swarm configuration:

swarms autoswarm --task "Build a content analysis pipeline" --model gpt-4

Show All Commands

Display all available CLI features:

swarms show-all

Output Handling

Capture Output to File

swarms llm-council --task "Evaluate cloud providers" > analysis.txt 2>&1

JSON Output Processing

swarms llm-council --task "Compare databases" | python -c "
import sys
import json
# Process output as needed
for line in sys.stdin:
    print(line.strip())
"

Pipe to Other Tools

swarms heavy-swarm --task "Research topic" | tee research.log | grep "RESULT"

Troubleshooting

Common Issues

Issue	Solution
"Command not found"	Ensure `pip install swarms` completed successfully
"API key not set"	Export `OPENAI_API_KEY` environment variable
"Task cannot be empty"	Always provide `--task` argument
Timeout errors	Check network connectivity and API rate limits

Debug Mode

Run with verbose output for debugging:

swarms llm-council --task "Your query" --verbose 2>&1 | tee debug.log

Next Steps

Explore CLI Reference Documentation for all commands
See CLI Examples for more use cases
Learn about LLM Council Python API
Try Heavy Swarm Documentation for advanced configuration

6.8 KiB Raw Blame History