YoMo

YoMo is an open-source LLM Function Calling Framework for building scalable and ultra-fast AI Agents. 💚 We care about: Empowering Exceptional Customer Experiences in the Age of AI

We believe that seamless and responsive AI interactions are key to delivering outstanding customer experiences. YoMo is built with this principle at its core, focusing on speed, reliability, and scalability.

🌶 Features

🚀 Getting Started

Let's build a simple AI agent with LLM Function Calling to provide weather information:

Step 1. Install CLI

curl -fsSL https://get.yomo.run | sh

Verify the installation:

yomo version

Step 2. Start the server

Create a configuration file my-agent.yaml (you can start from agent.template.yaml):

zipper:
  host: "0.0.0.0"
  port: 9000
  tls: {}
  auth_token: "SECRET_TOKEN"

http_api:
  host: "0.0.0.0"
  port: 9001
  enable_tool_api: false

llm_providers:
  - type: "openai"
    model_id: "gemma-4-31B-it"
    default: true
    params:
      model: "google/gemma-4-31B-it"
      base_url: "http://localhost:11434"
      api_key: ""

Launch the server:

yomo serve -c my-agent.yaml

Step 3. Implement the LLM Function Calling

Create a type-safe function that retrieves weather data:

export const description = 'Get the current weather for `city`'

export type Argument = {
  /**
   * The name of the city to be queried
   */
  city: string;
}

export async function handler(args: Argument) {
  // Simulate a weather API call
  let temperature = Math.floor(Math.random() * 41)

  // Return the result to LLM
  return { 
    city: args.city, 
    temperature: temperature,
    feels_like: 11.9,
    rain: false,
  }
}

Finished, now, let's run it:

$ yomo run -n get-weather

Done, let's have a try

$ curl http://127.0.0.1:9000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer SECRET_TOKEN" \
-d '{
  "messages": [
    {
      "role": "user",
      "content": "I am going for a hike on the Yarra Bend Park Loop. What should I wear?"
    }
  ],
  "stream": false
}'

You'll receive a helpful response like this:

For your hike on the Yarra Bend Park Loop, the current weather is clear with a temperature of approximately 12.3°C (feels like 11.9°C). 

Here are some suggestions on what to wear: 

1. **Layers**: Start with a base layer such as a moisture-wicking t-shirt. Add a light sweater or fleece for warmth since it can be chilly. 
2. **Jacket**: Bring a lightweight jacket or windbreaker to keep warm, especially as it is breezy with a southeast wind at 6 km/h with gusts up to 14 km/h. 
3. **Pants**: Comfortable hiking pants or leggings will be suitable. 
4. **Footwear**: Wear sturdy hiking boots or shoes with good grip. 
5. **Accessories**: Consider a hat or beanie for warmth, and bring gloves if you tend to get cold easily. 
6. **Backpack**: Carry a small backpack with water, snacks, and any additional layers you might need. 

Since there is **no rain** expected, you shouldn't need waterproof gear, but it's always wise to check the latest forecast before heading out. Enjoy your hike!

Explore More Examples

Check out our Servereless LLM Function Calling Examples for more use cases and inspiration.

📚 Documentation

Read more about YoMo on yomo.run.

🎯 Focuses on Geo-distributed AI Inference Infra

It’s no secret that today’s users want instant AI inference, every AI application is more powerful when it response quickly. But, currently, when we talk about distribution, it represents distribution in data center. The AI model is far away from their users from all over the world.

If an application can be deployed anywhere close to their end users, solve the problem, this is Geo-distributed System Architecture:

🦸 Contributing

First off, thank you for considering making contributions. It's people like you that make YoMo better. There are many ways in which you can participate in the project, for example:

• File a bug report. Be sure to include information like what version of YoMo you are using, what your operating system is, and steps to recreate the bug.
• Suggest a new feature.
• Read our contributing guidelines to learn about what types of contributions we are looking for.
• We have also adopted a code of conduct that we expect project participants to adhere to.

Devleopment

• Build

  cargo build --release
  
  ./target/release/yomo --help
  

• Use Ollama as the LLM provider:

  ollama pull qwen3.5
  

• Run YoMo server:

  RUST_LOG=debug ./target/release/yomo serve
  

• Initialize a Serverless LLM Tool project:

  ./target/release/yomo init
  

• Edit tool source:

  vim ./app/src/app.ts
  

• Run YoMo serverless tool:

  RUST_LOG=debug ./target/release/yomo run --name get-weather ./app
  

• Send an agent request:

  curl \
    --request POST \
    --url http://127.0.0.1:9001/v1/chat/completions \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "qwen3.5",
      "messages": [
          {
              "role": "user",
              "content": "How is the weather in London?"
          }
        ]
      }'
  

License

Apache License 2.0