Sekuire Rust SDK
Rust SDK for building AI agents with the Sekuire Trust Protocol.
Installation
Add to your Cargo.toml:
[]
= "0.1"
= { = "1", = ["full"] }
Quick Start
Config-First Approach (Recommended)
Create a sekuire.yml file:
project:
name: "my-agent"
version: "1.0.0"
agents:
assistant:
name: "AI Assistant"
system_prompt: "./prompts/assistant.md"
tools: "./tools.json"
llm:
provider: "openai"
model: "gpt-4-turbo"
api_key_env: "OPENAI_API_KEY"
temperature: 0.7
memory:
type: "buffer"
max_messages: 10
Load and use your agent:
use get_agent;
async
Features
- ✅ 4 LLM Providers: OpenAI, Anthropic, Google, Ollama
- ✅ Built-in Tools: Calculator, Web Search, HTTP, File Read
- ✅ Config-First: Declarative YAML configuration
- ✅ Type-Safe: Rust's type system
- ✅ Async: Built on Tokio
API Reference
get_agent(name, config_path)
Load a single agent from configuration.
let agent = get_agent.await?;
get_agents(config_path)
Load all agents from configuration.
let agents = get_agents.await?;
SekuireAgent
Main agent struct with methods:
chat(&mut self, message, options)- Send message and get responseget_history(&self)- Get conversation historyclear_history(&mut self)- Clear historyget_llm_provider(&self)- Get provider nameget_model_name(&self)- Get model nameget_tools(&self)- Get tool names
Built-in Tools
use ;
use HashMap;
use Value;
async
Development
# Build
# Test
# Run examples
Standalone sample config: examples/minimal-agent/ (sekuire.yml, system_prompt.md, tools.json).
License
Apache-2.0