Manual Install - CowAgent

Source Code Deployment

1. Clone the project

git clone https://github.com/zhayujie/CowAgent
cd CowAgent/

For network issues, use the mirror: https://gitee.com/zhayujie/CowAgent

2. Install dependencies

Core dependencies (required):

pip3 install -r requirements.txt

Optional dependencies (recommended):

pip3 install -r requirements-optional.txt

3. Install Cow CLI

Install the command-line tool for managing services and skills:

pip3 install -e .

Then use the cow command:

cow help

This step is recommended. After installation you can use cow start, cow stop, cow update to manage the service, and cow skill to manage skills. Without the CLI, you can use ./run.sh or python3 app.py to run.

4. Configure

Copy the config template and edit:

cp config-template.json config.json

Fill in model API keys, channel type, and other settings in config.json. See the model docs for details.

5. Run

Using Cow CLI (recommended):

cow start

Or run locally in foreground:

python3 app.py

By default, the Web console starts. Access http://localhost:9899 to chat. Background run on server (without CLI):

nohup python3 app.py & tail -f nohup.out

Deploying on a server? By default web_host only listens on 127.0.0.1 (local access). Set web_host to 0.0.0.0 in config.json to make the console reachable from outside, and set web_password to protect it. Don’t forget to open port 9899 in your firewall or security group — ideally restricted to specific IPs.

Docker Deployment

Docker deployment does not require cloning source code or installing dependencies. For Agent mode, source deployment is recommended for broader system access.

Requires Docker and docker-compose.

1. Download config

curl -O https://cdn.link-ai.tech/code/cow/docker-compose.yml

Edit docker-compose.yml with your configuration. 2. Start container

sudo docker compose up -d

3. View logs

sudo docker logs -f chatgpt-on-wechat

Running in Docker? Set WEB_HOST to 0.0.0.0 in docker-compose.yml so the console is reachable from outside the container, and set WEB_PASSWORD to protect it. Make sure port 9899 is mapped to the host and open in your firewall or security group.

Core Configuration

{
  "channel_type": "web",
  "model": "deepseek-v4-flash",
  "deepseek_api_key": "",
  "agent": true,
  "agent_workspace": "~/cow",
  "agent_max_context_tokens": 40000,
  "agent_max_context_turns": 30,
  "agent_max_steps": 15,
  "cow_lang": "auto"
}

Parameter	Description	Default
`channel_type`	Channel type	`web`
`model`	Model name	`deepseek-v4-flash`
`agent`	Enable Agent mode	`true`
`agent_workspace`	Agent workspace path	`~/cow`
`agent_max_context_tokens`	Max context tokens	`40000`
`agent_max_context_turns`	Max context turns	`30`
`agent_max_steps`	Max decision steps per task	`15`
`cow_lang`	Language for the UI, command text and system prompts; `auto` to detect, or set `zh` / `en`	`auto`

Full configuration options are in the project config.py.

​Source Code Deployment

​1. Clone the project

​2. Install dependencies

​3. Install Cow CLI

​4. Configure

​5. Run

​Docker Deployment

​Core Configuration

Source Code Deployment

1. Clone the project

2. Install dependencies

3. Install Cow CLI

4. Configure

5. Run

Docker Deployment

Core Configuration