Show HN:Rowboat——开源多智能体系统IDE
Show HN: Rowboat – Open-source IDE for multi-agent systems

原始链接: https://github.com/rowboatlabs/rowboat

从rowboat导入Client,StatefulChat 从rowboat.schema导入UserMessage,SystemMessage # 初始化客户端 client = Client(host="http://localhost:3000", project_id="<PROJECT_ID>", api_key="<API_KEY>") # 创建一个有状态的聊天会话(推荐) chat = StatefulChat(client) response = chat.run("伦敦的天气怎么样?") print(response) # 或者使用低级客户端API messages = [SystemMessage(role='system', content="你是一个乐于助人的助手"), UserMessage(role='user', content="你好,你好吗?")] # 获取回复 response = client.chat(messages=messages) print(response.messages[-1].content)

Rowboat是一个开源的、AI辅助的IDE,用于构建和管理多智能体系统。由Arjun、Ramnique和Akhilesh创建,Rowboat允许用户从单个智能体扩展到协同工作的团队,利用MCP工具并持续改进。它通过提供迭代开发平台来解决构建可靠的智能体系统的挑战,类似于Cursor之于代码。 其主要功能包括:类似代码的智能体指令方法,其中包含用于引用其他智能体、工具和提示的特殊关键字;集成的MCP服务器和Webhook功能,用于访问工具;以及LLM驱动的工具响应模拟,用于快速测试。Rowboat的playground方便实时调试,并提供基于聊天的副驾驶,用于根据反馈改进智能体指令。在Rowboat中构建的系统可以通过HTTP API或Python SDK集成。Rowboat采用Apache 2.0许可证,允许自托管和修改。

原文
from rowboat import Client, StatefulChat
from rowboat.schema import UserMessage, SystemMessage

# Initialize the client
client = Client(
    host="http://localhost:3000",
    project_id="<PROJECT_ID>",
    api_key="<API_KEY>"
)

# Create a stateful chat session (recommended)
chat = StatefulChat(client)
response = chat.run("What's the weather in London?")
print(response)

# Or use the low-level client API
messages = [
    SystemMessage(role='system', content="You are a helpful assistant"),
    UserMessage(role='user', content="Hello, how are you?")
]

# Get response
response = client.chat(messages=messages)
print(response.messages[-1].content)
联系我们 contact @ memedata.com