LLM-Rosetta

English Version | 中文版

LLM-Rosetta — A Python library for converting between different LLM provider API formats using a hub-and-spoke architecture with a central IR (Intermediate Representation).

Full Documentation

Full documentation is available at:

• English: https://llm-rosetta.readthedocs.io/en/latest/
• 中文: https://llm-rosetta.readthedocs.io/zh-cn/latest/

The Problem

When building applications that work with multiple LLM providers, you face an N² conversion problem — every provider pair requires its own conversion logic. LLM-Rosetta solves this with a hub-and-spoke approach: each provider only needs a single converter to/from the shared IR format.

Provider A ──→ IR ──→ Provider B
Provider C ──→ IR ──→ Provider D
         ... and so on

Supported Providers

Ollama & Other OpenAI-Compatible Servers

LLM-Rosetta works out of the box with any server that exposes OpenAI-compatible endpoints. Ollama (v0.13+) is a great example — it supports three of the four API formats that LLM-Rosetta converts between:

Other compatible servers include HuggingFace TGI, vLLM, and LM Studio.

Features

• Unified IR format for messages, tool calls, and content parts
• Bidirectional conversion: requests to provider format, responses from provider format
• Streaming support with typed stream events
• Auto-detection of provider from request/response objects
• Support for text, images, tool calls, and tool results
• Zero required dependencies (only typing_extensions); provider SDKs are optional

Compliance Testing

llm-comply is a companion tool that validates LLM API endpoints against official specs. Use it to verify that a gateway or proxy correctly implements the OpenAI Chat, Open Responses, Anthropic Messages, and Google GenAI formats.

pip install llm-comply

# Test your gateway endpoint
llm-comply -u https://your-gateway/v1 -k $API_KEY -m your-model --format openai-chat

A hosted version is available at llm-comply.service.oaklight.top. An on-demand Compliance workflow is also included in CI.

Installation

Basic Installation

Install the core package (requires Python >= 3.8):

pip install llm-rosetta

Installing with Provider SDKs

# Individual providers
pip install llm-rosetta[openai]
pip install llm-rosetta[anthropic]
pip install llm-rosetta[google]

# All providers
pip install llm-rosetta[openai,anthropic,google]

Optional Dependencies

Quick Start

from llm_rosetta import OpenAIChatConverter, AnthropicConverter

# Create converters
openai_conv = OpenAIChatConverter()
anthropic_conv = AnthropicConverter()

# Convert an OpenAI response to IR, then to Anthropic format
ir_messages = openai_conv.response_from_provider(openai_response)
anthropic_request = anthropic_conv.request_to_provider(ir_messages)

Auto-Detection

from llm_rosetta import convert, detect_provider

# Automatically detect provider and convert
provider = detect_provider(some_response)
ir_messages = convert(some_response, direction="from_provider")

Cross-Provider Conversation

from llm_rosetta import OpenAIChatConverter, GoogleGenAIConverter
from llm_rosetta.types.ir import Message, ContentPart

# Shared IR message history
ir_messages = []

# Turn 1: Ask OpenAI
ir_messages.append(Message(role="user", content=[ContentPart(type="text", text="Hello!")]))
openai_request = openai_conv.request_to_provider({"messages": ir_messages})
openai_response = openai_client.chat.completions.create(**openai_request)
ir_messages.extend(openai_conv.response_from_provider(openai_response))

# Turn 2: Continue with Google — full context preserved
google_request = google_conv.request_to_provider({"messages": ir_messages})

Citation

If you use LLM-Rosetta in your research, please cite our paper:

@article{ding2026llm,
  title={LLM-Rosetta: A Hub-and-Spoke Intermediate Representation for Cross-Provider LLM API Translation},
  author={Ding, Peng},
  journal={arXiv preprint arXiv:2604.09360},
  year={2026}
}

Contributing

Contributions are welcome! Please visit the GitHub repository to get started.

License

This project is licensed under the MIT License — see the LICENSE file for details.