返回资讯中心
外部精选
软件工程
#开发者实时流

Padwan AI 发布轻量 Python LLM 客户端,支持 HTTP/2 和 HTTP/3

来源标题:Show HN: Padwan AI, an LLM Client for Python with HTTP/2 and HTTP/3

Padwan AI 发布了面向 Python 的异步 LLM 客户端,采用轻量设计,支持 HTTP/2 和 HTTP/3。它可对接 OpenAI、Gemini、Mistral、Grok、Anthropic 及任意 OpenAI 兼容 API,并内置 AgentSession 智能体循环,可直接挂载 MCP 工具与服务器。项目以 padwan-ai 包名发布,可通过 pip 或 uv 安装。

Hacker News 最新Orelus2026/11/10 · 7 天前5 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

Lightweight async client for OpenAI, Gemini, Mistral, Grok, Anthropic, ElevenLabs (experimental), Gradium (experimental), TypeSafe (JEV, experimental), and any OpenAI-compatible API.

Most LLM client libraries pull in a stack of dependencies and lock you into a single provider's SDK. Padwan AI takes a different approach:

export OPENAI_API_KEY="sk-..." uvx padwan-ai "Hello!" -m gpt-5.4-mini

from padwan_ai import LLMClient

async with LLMClient(model="gpt-5.5") as client: response, usage = await client.complete_chat( [{"role": "user", "content": "Hello!"}] ) print(response["content"])

Installation

pip install padwan-ai

Or with uv:

uv add padwan-ai

Agentic loop

AgentSession wraps a conversation with the loop that calls the LLM, dispatches any tool calls, feeds the results back, and repeats until the model produces a plain text answer. It accepts individual McpTool instances and whole McpTransport servers in the same list, transports are entered as part of the session lifecycle:

from padwan_ai import AgentSession, LLMClient, McpStdio

async with AgentSession( client=LLMClient(model="gpt-5.5"), mcp_tools=[McpStdio(command="uvx", args=["weather-mcp"])], system="You have access to weather tools.", ) as session: text = await session.send("What is the weather in Paris?")

See the Agents page for approval hooks, parallel execution, and snapshot persistence.

Connect to MCP tool servers over streamable HTTP or stdio:

from padwan_ai import McpStreamable, McpStdio

async with McpStreamable(url="https://mcp.example.com/mcp", token="sk-...") as mcp: result = await mcp.tools[0].handler({"query": "test"})

See the MCP page for architecture diagrams, the dual-channel design of McpStreamable, the stdio reader model, and the reconnection flow.

The interactive CLI/TUI is available as a separate package: padwan-cli.

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →