Skillberry

Projects /

llm-switchboard

One client for many LLM providers — tool calls, structured outputs, retries.

View on GitHub

  • LanguagePython
  • Statusavailable on PyPI
  • LicenseApache-2.0

LLM Switchboard is a small Python library for building reliable LLM apps: call different model providers through one consistent interface.

from llm_switchboard.llm import get_llm

client = get_llm("litellm")(model_name="openai/gpt-4o-mini")
print(client.generate("Summarize the role of a model gateway."))

Highlights

  • One interface — LiteLLM (default), OpenAI, Azure OpenAI, Ollama and watsonx behind the same API.
  • Sync and async generation with standardized tool calling.
  • Schema-validated outputs — structured output with validation and retries.
  • Debuggable — provider-specific parameter mapping and configurable logging hooks.