swarms
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
What is swarms?
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
Overview of swarms
What it is
Swarms is an enterprise-grade, production-ready multi-agent orchestration framework for Python. It allows developers to build, deploy, and scale high-performance multi-agent systems with support for sequential, concurrent, and hierarchical architectures.
Key features
- Production-ready harnesses for sequential, concurrent, and hierarchical multi-agent architectures
- Seamless framework compatibility and integrations with MCP, x402, and skills
- Autonomous agent mode with
max_loops="auto"for open-ended tasks - MCP integration: agents can use external tools via MCP servers, and agents can be deployed as MCP servers with authentication
- Optional speedups via
swarms[fast](RouteHub for faster model calls, rustworkx for faster graph workflows) - Docker image available for
linux/amd64andlinux/arm64
Use cases
- Multi-agent collaboration for research, writing, and analysis
- Open-ended research or analysis tasks requiring iterative refinement
- Deploying agents as MCP servers for other agents or MCP hosts to call
- Building sequential workflows where agent outputs feed into subsequent agents
Getting started
### pip
$ pip3 install -U swarms
### uv (recommended)
$ uv pip install swarms
### poetry
$ poetry add swarms
### From source
$ git clone https://github.com/kyegomez/swarms.git
$ cd swarms
$ pip install -r requirements.txt
### With optional speedups
$ pip3 install -U "swarms[fast]"
### Docker
$ docker pull swarmscorp/swarms:latest
$ docker run --rm -e OPENAI_API_KEY -v "$PWD:/app" swarmscorp/swarms python agent.py
License and pricing
Licensed under Apache-2.0. Open source and free to use.
Based on the project's public README and repository metadata.