Swarms AI - Enterprise Multi-Agent Framework
Build, deploy, and scale autonomous AI agent swarms with unprecedented control and efficiency
swarms
The Enterprise-Grade Multi-Agent Infrastructure Stack
Features
Swarms has pioneered world-class infrastructure for multi-agent collaboration such as communication protocols, optimized runtimes, memory systems, and simulation environments.
Installation
Get started with Swarms in seconds. Choose your preferred language and install the framework.
Python Installation
Install the core Swarms Python framework with pip.
pip3 install -U swarms
Code Examples
See Swarms in action with real-world examples and production-ready code snippets
SWARMS PYTHON
Core Swarms Python Framework
The original Swarms framework in Python with full backwards compatibility with LangChain, AutoGen, and other popular frameworks. Build complex multi-agent workflows with just a few lines of code.
from swarms import Agent, SequentialWorkflow # Agent 1: The Researcher researcher = Agent( agent_name="Researcher", system_prompt="Your job is to research the provided topic and provide a detailed summary.", model_name="gpt-4o-mini", ) # Agent 2: The Writer writer = Agent( agent_name="Writer", system_prompt="Your job is to take the research summary and write a beautiful, engaging blog post about it.", model_name="gpt-4o-mini", ) # Create a sequential workflow where the researcher's output feeds into the writer's input workflow = SequentialWorkflow(agents=[researcher, writer]) # Run the workflow on a task final_post = workflow.run("The history and future of artificial intelligence") print(final_post)
use std::env; use anyhow::Result; use swarms_rs::llm::provider::openai::OpenAI; use swarms_rs::structs::concurrent_workflow::ConcurrentWorkflow; #[tokio::main] async fn main() -> Result<()> { let client = OpenAI::from_url(base_url, api_key) .set_model("deepseek-chat"); // Create specialized trading agents let market_analysis_agent = client .agent_builder() .agent_name("Market Analysis Agent") .system_prompt("You are a market analysis specialist...") .max_loops(1) .temperature(0.2) .build(); // Create concurrent workflow let workflow = ConcurrentWorkflow::builder() .name("Trading Strategy Workflow") .agents(vec![ Box::new(market_analysis_agent), Box::new(trade_strategy_agent), Box::new(risk_assessment_agent), ]) .build(); let result = workflow.run("BTC/USD analysis...").await?; println!("{}", serde_json::to_string_pretty(&result)?); Ok(()) }
SWARMS-RS
The First Multi-Agent Framework in Rust
Ultra-fast, memory-safe, and production-ready multi-agent framework built in Rust for maximum performance and reliability. Perfect for high-throughput enterprise applications.
SWARMS API
Ultra-Optimized Hosted Runtime
Enterprise-grade hosted API with ultra-optimized runtime for deploying and scaling your agent swarms in production. No infrastructure management required.
curl -X POST "https://api.swarms.world/v1/swarm/completions" \ -H "x-api-key: $SWARMS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "name": "Content Creation Pipeline", "description": "Sequential content creation from research to final output", "swarm_type": "SequentialWorkflow", "task": "Create a comprehensive blog post about the future of renewable energy", "agents": [ { "agent_name": "Research Specialist", "description": "Conducts thorough research on the topic", "system_prompt": "You are a research specialist...", "model_name": "gpt-4o", "max_loops": 1, "temperature": 0.3 }, { "agent_name": "Content Writer", "description": "Creates engaging written content", "system_prompt": "You are a skilled content writer...", "model_name": "gpt-4o", "max_loops": 1, "temperature": 0.6 } ], "max_loops": 1 }'

Marketplace Stats
SWARMS MARKETPLACE
Buy & Sell Agents, Prompts & More
Discover, buy, and sell agents, prompts, tools, and components on swarms.world - the premier marketplace for AI agents. Monetize your creations and access specialized agents built by the community.
Cookbook & Templates
Get started quickly with curated examples, templates, and implementation guides
READY TO |
Join thousands of developers building the future of AI with the most advanced multi-agent framework ever created
Try Swarms for free
Sign up for our newsletter and get $20 in free credits, plus exclusive updates, technical guides, blogs, and more!