Crate openheim 

openheim

A fast, multi-provider LLM agent runtime written in Rust.

Quick start

use openheim::{OpenheimClient, Result};

#[tokio::main]
async fn main() -> Result<()> {
    let client = OpenheimClient::builder()
        .provider("openai")
        .api_key("sk-...")
        .model("gpt-4o")
        .build()
        .await?;

    let session = client.new_session().start().await?;
    session.prompt("List the files in the current directory.", |_update| {}).await?;

    Ok(())
}

Providers

Provider	Value	Default model
OpenAI	"openai"	gpt-4o
Anthropic	"anthropic"	claude-sonnet-4-6
Google	"gemini"	gemini-2.0-flash
Compatible	any string	set via .model()

Configuration file

By default openheim loads ~/.openheim/config.toml. Use OpenheimClient::from_config to load from a custom path, or set individual fields via the builder for fully programmatic configuration.

MCP servers

External tools are registered as MCP servers and namespaced as {server_name}__{tool_name}. They are automatically available in every agent session.

Key types

• OpenheimClient / OpenheimBuilder — main entry point
• SessionHandle — send prompts and receive streaming SessionUpdate events
• LlmClient — implement to add a custom provider
• RagContext — conversation history and skill injection
• Error / Result — unified error type

Re-exports

pub use config::AgentConfig;

pub use config::AppConfig;

pub use config::McpServerConfig;

pub use config::ModelsInfo;

pub use core::agent;

pub use core::llm;

pub use core::models;

pub use error::Error;

pub use error::Result;

pub use llm::AnthropicClient;

pub use llm::GeminiClient;

pub use llm::LlmClient;

pub use llm::OpenAiClient;

pub use llm::OpenAiCompatibleClient;

pub use rag::Conversation;

pub use rag::ConversationMeta;

pub use rag::HistoryManager;

pub use rag::PromptBuilder;

pub use rag::RagContext;

pub use client::OpenheimBuilder;

pub use client::OpenheimClient;

pub use client::SessionBuilder;

pub use client::SessionHandle;

pub use models::*;

Modules

acp

client

config

core

error

mcp

rag

Conversation history and skill injection for agent prompts.

tools

transport

tui

Structs

AcpToolCall

Represents a tool call that the language model has requested.

ContentChunk

A streamed item of content

SessionInfo

Information about a session returned by session/list

ToolCallUpdate

An update to an existing tool call.

Enums

ContentBlock

Content blocks represent displayable information in the Agent Client Protocol.

SessionUpdate

Different types of updates that can be sent during session processing.

ToolCallStatus

Execution status of a tool call.