My Brain Cells

Easiest (and best) learning materials for anyone with a curiosity for machine learning and artificial intelligence, Deep learning, Programming, and other fun life hacks.

ChatDev – Build A Startup With One Prompt!!

In the fast-paced world of technology and startups, the ability to develop and iterate on ideas quickly is crucial. But what if you could take that speed to a whole new level? Imagine being able to build a startup with just one prompt. That’s where ChatDev comes in. In this blog post, we’ll walk you through the process of installing ChatDev and explore how it can help you turn your ideas into reality with astonishing speed and efficiency.

What Is ChatDev?

Create Customized Software using Natural Language Ideas (through LLM-powered Multi-Agent Collaboration)

Why ChatDev?

  • ChatDev stands as a virtual software company that operates through various intelligent agents holding different roles, including Chief Executive Officer , Chief Product Officer , Chief Technology Officer , programmer , reviewer , tester , art designer . These agents form a multi-agent organizational structure and are united by a mission to “revolutionize the digital world through programming.” The agents within ChatDev collaborate by participating in specialized functional seminars, including tasks such as designing, coding, testing, and documenting.
  • The primary objective of ChatDev is to offer an easy-to-use, highly customizable and extendable framework, which is based on large language models (LLMs) and serves as an ideal scenario for studying collective intelligence.

Installing ChatDev

To get started, follow these steps:

1. Clone the GitHub Repository

git clone

2. Set Up Python Environment: 

conda create -n ChatDev_conda_env python=3.9 -y conda activate ChatDev_conda_env

3. Install Dependencies: 

cd ChatDev pip3 install -r requirements.txt

4. Set OpenAI API Key: 

Export your OpenAI API key as an environment variable. Replace "your_OpenAI_API_key" with your actual API key. Remember that this environment variable is session-specific, so you need to set it again if you open a new terminal session.

On Unix/Linux:

export OPENAI_API_KEY="your_OpenAI_API_key" 

On Windows:


5. Build Your Software: 

Use the following command to initiate the building of your software, replacing [description_of_your_idea] with your idea’s description and [project_name] with your desired project name:

On Unix/Linux:

python3 --task "[description_of_your_idea]" --name "[project_name]" 

On Windows:

python --task "[description_of_your_idea]" --name "[project_name]"

6. Run Your Software: 

Once generated, you can find your software in the WareHouse directory under a specific project folder, such as project_name_DefaultOrganization_timestamp. Run your software using the following command within that directory:

On Unix/Linux:

cd WareHouse/project_name_DefaultOrganization_timestamp python3 

On Windows:

cd WareHouse/project_name_DefaultOrganization_timestamp python 

Local Demo:

  • you can start a flask app fist get a local demo, including enhanced visualized logs, replay demo, and a simple ChatChain Visualizer.
python3 online_log/

then go to Local Demo Website to see an online visualized version of logs

  • You can also goto the ChatChain Visualizer on this page and upload any ChatChainConfig.json under CompanyConfig/ to get a visualization on this chain, such as:
  • You can also goto the Chat Replay page to replay log file in the software folder
    • click the File Upload bottom to upload a log, then click Replay
    • The replay only shows the dialogues in natural languages between agents, it will not contain debug logs.


Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top