同步操作将从 Gitee 极速下载/Auto-GPT 强制同步,此操作会覆盖自 Fork 仓库以来所做的任何修改,且无法恢复!!!
确定后同步将在后台操作,完成时将刷新页面,请耐心等待。
This document describes how to interact with the project's CLI (Command Line Interface). It includes the types of outputs you can expect from each command. Note that the agents stop
command will terminate any process running on port 8000.
Running the ./run
command without any parameters will display the help message, which provides a list of available commands and options. Additionally, you can append --help
to any command to view help information specific to that command.
./run
Output:
Usage: cli.py [OPTIONS] COMMAND [ARGS]...
Options:
--help Show this message and exit.
Commands:
agent Commands to create, start and stop agents
benchmark Commands to start the benchmark and list tests and categories
setup Installs dependencies needed for your system.
If you need assistance with any command, simply add the --help
parameter to the end of your command, like so:
./run COMMAND --help
This will display a detailed help message regarding that specific command, including a list of any additional options and arguments it accepts.
./run setup
Output:
Setup initiated
Installation has been completed.
This command initializes the setup of the project.
a. List All Agents
./run agent list
Output:
Available agents: 🤖
🐙 forge
🐙 autogpt
Lists all the available agents.
b. Create a New Agent
./run agent create my_agent
Output:
🎉 New agent 'my_agent' created and switched to the new directory in autogpts folder.
Creates a new agent named 'my_agent'.
c. Start an Agent
./run agent start my_agent
Output:
... (ASCII Art representing the agent startup)
[Date and Time] [forge.sdk.db] [DEBUG] 🐛 Initializing AgentDB with database_string: sqlite:///agent.db
[Date and Time] [forge.sdk.agent] [INFO] 📝 Agent server starting on http://0.0.0.0:8000
Starts the 'my_agent' and displays startup ASCII art and logs.
d. Stop an Agent
./run agent stop
Output:
Agent stopped
Stops the running agent.
a. List Benchmark Categories
./run benchmark categories list
Output:
Available categories: 📚
📖 code
📖 safety
📖 memory
... (and so on)
Lists all available benchmark categories.
b. List Benchmark Tests
./run benchmark tests list
Output:
Available tests: 📚
📖 interface
🔬 Search - TestSearch
🔬 Write File - TestWriteFile
... (and so on)
Lists all available benchmark tests.
c. Show Details of a Benchmark Test
./run benchmark tests details TestWriteFile
Output:
TestWriteFile
-------------
Category: interface
Task: Write the word 'Washington' to a .txt file
... (and other details)
Displays the details of the 'TestWriteFile' benchmark test.
d. Start Benchmark for the Agent
./run benchmark start my_agent
Output:
(more details about the testing process shown whilst the test are running)
============= 13 failed, 1 passed in 0.97s ============...
Displays the results of the benchmark tests on 'my_agent'.
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。