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

Provider	API Standard	Request	Response	Streaming
OpenAI	Chat Completions	✅	✅	✅
OpenAI	Responses API	✅	✅	✅
Anthropic	Messages API	✅	✅	✅
Google	GenAI API	✅	✅	✅

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:

Ollama Endpoint	LLM-Rosetta Converter	Since
`/v1/chat/completions`	`openai_chat`	Early versions
`/v1/responses`	`openai_responses`	v0.13.3
`/v1/messages`	`anthropic`	v0.14.0

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

Extra	Packages	Description
`openai`	`openai`	OpenAI Chat Completions & Responses API
`anthropic`	`anthropic`	Anthropic Messages API
`google`	`google-genai`	Google GenAI API

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.

Release files for llm-rosetta 0.10.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llm-rosetta 0.10.0
File	Size	Uploaded
llm_rosetta-0.10.0.tar.gz	517.3 kB	Aug 26, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for llm-rosetta 0.10.0
File	Interpreter	ABI	Platform	Reset
llm_rosetta-0.10.0-py3-none-any.whl 578.1 kB Aug 26, 2026	Python 3	none	any	Details

Total release size: 1.1 MB

Release files / llm_rosetta-0.10.0.tar.gz

Download URL	llm_rosetta-0.10.0.tar.gz
Size	517.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`972ab813674a78a14d18095b2c8117c1beb2863fddb2c6d2a2a37ca3897229dc`
BLAKE2b-256 checksum How to use checksums	`f2581ce69d89679eb8df3d129d60467b083635234a125b9f777c9ee369bbd514`
Upload date	Aug 26, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/Oaklight/llm-rosetta
Publishing commit: github.com/Oaklight/llm-rosetta/tree/6738450ecec307e230bbab380ae8fd21ecf45955

Workflow

Publishing configuration: github.com/Oaklight/llm-rosetta/blob/6738450ecec307e230bbab380ae8fd21ecf45955/.github/workflows/release.yml
Publishing logs: github.com/Oaklight/llm-rosetta/actions/runs/33019775640/attempts/1

Artifact

Subject: llm_rosetta-0.10.0.tar.gz
SHA-256 checksum: 972ab813674a78a14d18095b2c8117c1beb2863fddb2c6d2a2a37ca3897229dc Verifying attestations

Release files / llm_rosetta-0.10.0-py3-none-any.whl

Download URL	llm_rosetta-0.10.0-py3-none-any.whl
Size	578.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`b170ea01e724a1679f3ac0c13426eaac4f9c6b69241692d6cd92842587325a08`
BLAKE2b-256 checksum How to use checksums	`c71cf0cb43060c24b05bfe233aaa9255cd8cc819cbe736aa7472bb7103e3de4b`
Upload date	Aug 26, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/Oaklight/llm-rosetta
Publishing commit: github.com/Oaklight/llm-rosetta/tree/6738450ecec307e230bbab380ae8fd21ecf45955

Workflow

Publishing configuration: github.com/Oaklight/llm-rosetta/blob/6738450ecec307e230bbab380ae8fd21ecf45955/.github/workflows/release.yml
Publishing logs: github.com/Oaklight/llm-rosetta/actions/runs/33019775640/attempts/1

Artifact

Subject: llm_rosetta-0.10.0-py3-none-any.whl
SHA-256 checksum: b170ea01e724a1679f3ac0c13426eaac4f9c6b69241692d6cd92842587325a08 Verifying attestations