A framework for creating collaborative AI agent swarms
Project description
Multi-Swarm Framework
A powerful framework for creating collaborative AI agent swarms, supporting multiple LLM providers and advanced agent management capabilities.
Features
-
Multi-LLM Support
- Claude (Anthropic) integration with latest models
- Gemini (Google) integration with latest models
- Automatic model selection based on agent roles
-
Advanced Agency Management
- Flexible agent creation and configuration
- Sophisticated communication flows between agents
- State persistence and thread management
- Automated task distribution and coordination
-
Built-in Tools
- Code Interpreter for executing Python code
- File Search with RAG capabilities
- Docker integration for isolated environments
- Customizable tool creation framework
Installation
pip install multi-swarm
Quick Start
from multi_swarm import Agency, Agent
# Create agents with specific roles
ceo = Agent(
name="CEO",
description="Manages overall strategy and coordination",
llm_provider="claude",
provider_config={
"model": "claude-3-sonnet",
"api_version": "2024-03"
}
)
developer = Agent(
name="Developer",
description="Handles technical implementation",
llm_provider="gemini",
provider_config={
"model": "gemini-pro",
"api_version": "2024-01"
}
)
# Create agency with communication flows
agency = Agency([
ceo, # Entry point for user communication
[ceo, developer], # CEO can communicate with Developer
])
# Run the agency
agency.run()
Documentation
For detailed documentation, visit:
Requirements
- Python 3.8+
- Dependencies:
- anthropic>=0.18.1
- google-generativeai>=0.3.2
- pydantic>=2.0.0
- python-dotenv>=1.0.0
- docker>=6.1.0
- sentence-transformers>=2.2.0
- faiss-cpu>=1.7.4
- transformers>=4.38.0
- torch>=2.0.0
- numpy>=1.24.0
- click>=8.0.0
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contributing
Contributions are welcome! Please read our Contributing Guidelines and Code of Conduct.
Support
- Report issues on GitHub Issues
- Join discussions in GitHub Discussions
Authors
- Bart Van Spitaels (bart.vanspitaels@gmail.com)
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file multi_swarm-1.0.3.tar.gz.
File metadata
- Download URL: multi_swarm-1.0.3.tar.gz
- Upload date:
- Size: 163.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
559a6dad762cd919208d59f4401ab04326d5d38637e634132eba7d21777590fb
|
|
| MD5 |
06626c72d12a59574f71794ed21d78b1
|
|
| BLAKE2b-256 |
4d72832339bfe74d726a6f3b4caf039f31c59cda9748db341b508a2c1ac95ded
|
File details
Details for the file multi_swarm-1.0.3-py3-none-any.whl.
File metadata
- Download URL: multi_swarm-1.0.3-py3-none-any.whl
- Upload date:
- Size: 124.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f649df429528f40729b039e0d49e8b743be7666884064028d9828fc4a913e5a0
|
|
| MD5 |
364c4f4c2d4e47117f48b36da89a6989
|
|
| BLAKE2b-256 |
b8070af3bcc04889360aeb16743c953235280f6388d910aa65b83d372d2af81e
|