AGENTSDK

An open-source, provider-agnostic Rust library for building AI-powered applications, inspired by the Vercel AI SDK. Type-safe, framework-friendly, and ready to connect with 70+ AI providers.

To learn more about how to use the AGENTSDK, check out our Documentation and API Reference.

Features

• Agents & Tool Execution
• Prompt Templating
• Text Generation & Streaming
• Structured Output (JSON Schema)
• Embedding Model Support
• Compatible with Vercel AI SDK UI (React, Solid, Vue, Svelte, …)
• Supports 73+ providers, including Anthropic, Google, OpenAI, OpenRouter, xAI

Installation

cargo add agentsdk

Usage

Enable Providers of your choice such as OpenAI, Anthropic, Google, and more

Example with OpenAI provider

cargo add agentsdk --features openai

Basic Text Generation

use agentsdk::LanguageModelRequest;
use agentsdk::providers::OpenAI;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {

    let openai = OpenAI::gpt_5();

    let result = LanguageModelRequest::builder()
        .model(openai)
        .prompt("What is the meaning of life?")
        .build()
        .generate_text() // or stream_text() for streaming
        .await?;

    println!("Response: {:?}", result.text());
    Ok(())
}

Agents

Defining a Tool

Use the #[tool] macro to expose a Rust function as a callable tool.

use agentsdk::Tool;
use agentsdk::tool;

#[tool]
/// Get the weather information given a location
pub fn get_weather(location: String) -> Tool {
    let weather = match location.as_str() {
        "Tokyo" => 80,
        _ => 70,
    };
    Ok(weather.to_string())
}

Using Tools in an Agent

Register tools with an agent so the model can call them during its reasoning loop.

use agentsdk::{LanguageModelRequest, utils::step_count_is};
use agentsdk::providers::OpenAI;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {

    let result = LanguageModelRequest::builder()
        .model(OpenAI::gpt_4o())
        .system("You are a helpful assistant.")
        .prompt("What is the weather in New York?")
        .with_tool(get_weather())
        .stop_when(step_count_is(3)) // Limit agent loop to 3 steps
        .build()
        .generate_text()
        .await?;

    println!("Response: {:?}", result.text());
    Ok(())
}

### Prompts

The AGENTSDK prompt feature provides, file-based template system for managing AI prompts using the Tera template engine. It allows you to create reusable prompt templates with variable substitution, conditionals, loops, and template inclusion. See [Examples](https://agentsdk.rs/docs/concepts/prompt) for more template examples. Enable with `cargo add agentsdk --features prompt`

### Roadmap

- [ ] Image Model Request Support
- [ ] Voice Model Request Support
- [ ] Observability & OpenTelemetry (OTel) Support

## Contributing

We welcome contributions! Please see [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines.

## License

Licensed under the MIT License. See [LICENSE](./LICENSE) for details.