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

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

Why #

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:

• One dependency —niquests , nothing else. No provider SDKs: Padwan talks to each API directly.
• TypedDict-only — all request/response types are plainTypedDict s, no validation framework required. No runtime cost, full editor support.
• Multi-provider, extensible — supports the major providers (OpenAI, Gemini, Mistral, Grok, Anthropic) with a shared base class that makes adding new ones straightforward.

Features #

• Unified interface - Single API for multiple LLM providers
• Async-first - Built on async/await for high performance
• HTTP/2 and HTTP/3 - Automatic protocol negotiation vianiquests
• Fully typed - Complete type hints with Python 3.13+ generics
• Streaming support - Real-time token streaming for all providers
• Conversation management - Built-in conversation history handling
• Agentic loop -AgentSession drives multi-turn conversations with tool dispatch, parallel execution, approval hooks, and snapshot persistence
• MCP support - Streamable HTTP and stdio transports forModel Context Protocol tool servers
• Thinking models - Stream Gemini, Claude, Mistral, Grok and vLLM thought tokens separately via anon_thought callback
• Realtime voice - Speech-to-speech WebSocket sessions (OpenAI Realtime, Gemini Live, Grok Voice) viaRealtimeClient
• Text-to-speech - Single and two-speaker Gemini TTS viaGeminiClient.generate_speech (details ), ElevenLabs and Gradium TTS (REST, streaming and WebSocket), transcription and speech-to-speech, plus ElevenLabs sound effects and music, viaElevenLabsClient and GradiumClient

Supported Providers #

• ❌ = the provider offers it, Padwan does not implement it yet.
• ➖ = the provider has no such API (Gemini transcribes through chat audio input; Anthropic recommends Voyage AI for embeddings).
• ➕ = depends on the endpoint: the request is sent in OpenAI's wire format; support is up to the server.
• Realtime: Gradium's is speech-to-speech translation, not a voice-agent session; ElevenLabs and Gradium also stream TTS and STT over WebSocket.

Quick Example #

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

MCP (Model Context Protocol) #

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.

CLI / TUI #

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

uvx padwan-cli "Explain Python decorators" -m gemini-3.8-flash

uvx padwan-cli chat -m gpt-5.5