AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration
System Usage
Installation
Install with Docker (Recommended)
If you have installed docker and docker-compose on your machine, we recommend running AgentCoord in docker：
Step 1: Clone our project and start the servers:
git clone https://github.com/AgentCoord/AgentCoord.git
cd AgentCoord
docker-compose up
Step 2: Open http://localhost:8080/ to use the system.
Install on your machine
If you want to install and run AgentCoord on your machine without using docker:
Step 1: Clone the project
git clone https://github.com/AgentCoord/AgentCoord.git
cd AgentCoord
Step 2: Install required packages for the backend and frontend servers (check readme.md in ./frontend and ./backend folders)
Step 3: Run the backend and frontend servers separately (check readme.md in ./frontend and ./backend folders).
Step 4: Open http://localhost:8080/ to use the system.
Configuration
git clone https://github.com/AgentCoord/AgentCoord.git
cd AgentCoord
pip install -r requirements.txt
Configuration
LLM configuration
You can set the configuration (i.e. API base, API key, Model name, Max tokens, Response per minute) for default LLM in config\config.yaml. Currently, we only support OpenAI’s LLMs as the default model. We recommend using gpt-4-0125-preview as the default model (WARNING: the execution process of multiple agents may consume a significant number of tokens).
You can switch to a fast mode that uses the Mistral 8×7B model with hardware acceleration by Groq for the first time in strategy generation to strike a balance of response quality and efficiency. To achieve this, you need to set the FAST_DESIGN_MODE field in the yaml file as True and fill the GROQ_API_KEY field with the api key of Groq.
Agent configuration
Currently, we support config agents by role-prompting. You can customize your agents by changing the role prompts in AgentRepo\agentBoard_v1.json. We plan to support more methods to customize agents (e.g., supporting RAG, or providing a unified wrapper for customized agents).
More Papers & Projects for LLM-based Multi-Agent Collaboration
If you’re interested in LLM-based multi-agent collaboration and want more papers & projects for reference, you may check out the corpus collected by us: