Otter Bridge

Created By

Alex Pang8 months ago

OtterBridge is a lightweight, flexible server for connecting applications to various Large Language Model providers. Following the principles of simplicity and composability outlined in Anthropic's guide to building effective agents, OtterBridge provides a clean interface to LLMs while maintaining adaptability for different use cases. Currently supporting Ollama, with planned expansions to support other providers like ChatGPT and Claude.

# otterbridge

# llm-connector

Overview Content Tools Comments

Content

File Structure

├── .env.example           # Example environment variables
├── .gitignore             # Files to exclude from git
├── LICENSE                # Open source license (MIT, Apache, etc.)
├── README.md              # Project documentation
├── server.py              # MCP server implementation (previously fastmcp_server.py)
├── requirements.txt       # Python dependencies
└── src/                   # Source code directory
    ├── __init__.py        # Package initialization
    └── services/          # Services
        ├── __init__.py
        └── ollama.py      # Ollama service

OtterBridge

Currently supporting Ollama, with planned expansions to support other providers like ChatGPT and Claude.

Features

Provider-Agnostic: Designed to work with multiple LLM providers (currently Ollama, with ChatGPT and Claude coming soon)
Simple, Composable Design: Following best practices for LLM agent architecture
Lightweight Server: Built with FastMCP for reliable, efficient server implementation
Model Management: Easy access to model information and capabilities

Why "OtterBridge"?

Like otters who build connections between riverbanks, OtterBridge creates seamless pathways between your applications and various LLM providers. Just as otters are adaptable and resourceful, OtterBridge adapts to different LLM backends while providing consistent interfaces.

Prerequisites

Before installing OtterBridge, you need to have:

Ollama installed and running on the default port
uv installed for Python package management

Installation

Clone this repository:

git clone https://github.com/yourusername/otterbridge.git
cd otterbridge

Install dependencies using uv:

uv add -r requirements.txt

Create a .env file based on the provided .env.example:

cp .env.example .env

Configure your environment variables in the .env file.

Claude Desktop Integration

For Claude Desktop users, you'll need to add OtterBridge to your Claude Desktop configuration:

Open your Claude Desktop config file
Add the following configuration (adjust the path to match your local installation):

"otterbridge": {
    "command": "uv",
    "args": [
        "--directory",
        "C:\\Path\\To\\Your\\otterbridge",
        "run",
        "server.py"
    ]
}

Usage

Starting the Server

OtterBridge can be started in two ways:

Manual start for testing purposes: :**

uv run server.py

Automatic start with MCP clients:
- When using compatible MCP clients like Claude Desktop, OtterBridge will start automatically when needed

Available Tools

OtterBridge exposes the following tools via the Model Context Protocol (MCP):

chat: Send messages to LLMs and get AI-generated responses
list_models: Retrieve information about available language models

Tool Usage Examples

List Available Models

Example response:

{
    "status": "connected",
    "server_status": "online",
    "available_models": ["llama3", "llama3.1:8b", "codellama", "llama3.3", "qwen2.5"],
    "available_models_count": 5,
    "message": "Successfully retrieved available Ollama models"
}

Chat Completion

Example response:

{
    "role": "assistant",
    "content": "I'm doing well, thank you for asking! I'm here and ready to help you with any questions or tasks you might have. How can I assist you today?",
    "model": "llama3:latest"
}