✨ If you would like to help spread the word about Rig, please consider starring the repo!

[!WARNING] Here be dragons! As we plan to ship a torrent of features in the following months, future updates will contain breaking changes. With Rig evolving, we’ll annotate changes and highlight migration paths as we encounter them.

Table of contents

• Table of contents
• What is Rig?
• Features
• Runtime choices
• Who’s using Rig?
• Get Started
  • Simple example
• Integrations

What is Rig?

Rig is a Rust library for building scalable, modular, and ergonomic LLM-powered applications.

More information about this crate can be found in the official and crate API reference documentation.

Features

• Agentic workflows that can handle multi-turn streaming and prompting
• A classic agent runtime enabled by default
• Full GenAI Semantic Convention compatibility
• 20+ model providers, all under one singular unified interface
• 10+ vector store integrations, all under one singular unified interface
• Full support for LLM completion and embedding workflows
• Support for transcription, audio generation and image generation model capabilities
• Integrate LLMs in your app with minimal boilerplate
• Full WASM compatibility for the portable core and classic runtime

Runtime choices

Rig separates portable provider/backend contracts from agent orchestration:

• rig-core contains provider-neutral messages, completion models, portable tools, memory and vector-store contracts, and built-in provider mappings.
• rig-agent contains the classic builder, prompt/streaming traits, typed hooks, contextual tools, extraction, and the serializable AgentRun state machine. It remains enabled by default.

The root rig facade re-exports both at their familiar paths, so most code depends only on rig.

Who is using Rig?

Below is a non-exhaustive list of companies and people who are using Rig:

• St Jude - Using Rig for a chatbot utility as part of proteinpaint, a genomics visualisation tool.
• Coral Protocol - Using Rig extensively, both internally as well as part of the Coral Rust SDK.
• VT Code - VT Code is a Rust-based terminal coding agent with semantic code intelligence via Tree-sitter and ast-grep. VT Code uses rig for simplifying LLM calls and implementing the model picker.
• Con - Con is a GPU-accelerated terminal emulator with a built-in AI agent harness. It uses Rig as the provider abstraction layer for its integrated coding agents.
• Dria - a decentralised AI network. Currently using Rig as part of their compute node.
• Nethermind - Using Rig as part of their Neural Interconnected Nodes Engine framework.
• Neon - Using Rig for their app.build V2 reboot in Rust.
• Listen - A framework aiming to become the go-to framework for AI portfolio management agents. Powers the Listen app.
• Cairnify - helps users find documents, links, and information instantly through an intelligent search bar. Rig provides the agentic foundation behind Cairnify’s AI search experience, enabling tool-calling, reasoning, and retrieval workflows.
• Ryzome - Ryzome is a visual AI workspace that lets you build interconnected canvases of thoughts, research, and AI agents to orchestrate complex knowledge work.
• deepwiki-rs - Turn code into clarity. Generate accurate technical docs and AI-ready context in minutes—perfectly structured for human teams and intelligent agents.
• Cortex Memory - The production-ready memory system for intelligent agents. A complete solution for memory management, from extraction and vector search to automated optimization, with a REST API, MCP, CLI, and insights dashboard out-of-the-box.
• Ironclaw - A secure personal AI assistant
• ilert - Incident management & alerting platform. Uses Rig as the multi-provider abstraction in its agentic LLM proxy powering ilert AI.
• Archestra - MCP-native secure AI platform. Uses Rig in its agentic benchmark.

For a curated list of Rig projects, libraries, tools, articles, and production users, check out awesome-rig.

Are you also using Rig? Open an issue to have your name added!

Get Started

Use the root rig facade when you want feature-gated access to companion crates, or use rig-core directly when you only need the core provider abstractions.

cargo add rig
# or: cargo add rig-core

Simple example

use rig::prelude::*;
use rig::providers::openai;

#[tokio::main]
async fn main() -> Result<(), anyhow::Error> {
    // Create OpenAI client
    let client = openai::Client::from_env()?;

    // Create agent with a single context prompt
    let comedian_agent = client
        .agent(openai::GPT_5_2)
        .preamble("You are a comedian here to entertain the user using humour and jokes.")
        .build();

    // Prompt the agent and print the response
    let response = comedian_agent.prompt("Entertain me!").await?;

    println!("{response}");

    Ok(())
}

Note using #[tokio::main] requires you enable tokio’s macros and rt-multi-thread features or just full to enable all features (cargo add tokio --features macros,rt-multi-thread).

You can find more examples in each crate’s examples directory (for example, examples). Provider-specific integration coverage lives under tests/providers, with cassette-backed tests that replay offline by default and live-only tests kept separate when real provider APIs are still required. See tests/README.md for test target, replay, record, and cassette safety commands. More detailed use case walkthroughs are regularly published on our Dev.to Blog and added to Rig’s official documentation at rig.rs/docs.

Supported Integrations

The root rig facade exposes companion crates behind one feature per integration:

rig = { version = "0.36.0", features = ["lancedb", "fastembed"] }

Integration	Crate	Feature	Module path
AWS Bedrock	rig-bedrock	bedrock	rig::bedrock
AWS S3Vectors	rig-s3vectors	s3vectors	rig::s3vectors
Candle (local Llama/SmolLM2/Qwen3 tools)	rig-candle	candle	rig::candle
Cloudflare Vectorize	rig-vectorize	vectorize	rig::vectorize
FastEmbed	rig-fastembed	fastembed	rig::fastembed
Google Gemini gRPC	rig-gemini-grpc	gemini-grpc	rig::gemini_grpc
Google Vertex AI	rig-vertexai	vertexai	rig::vertexai
HelixDB	rig-helixdb	helixdb	rig::helixdb
LanceDB	rig-lancedb	lancedb	rig::lancedb
Memory policies	rig-memory	memory	rig::memory
Milvus	rig-milvus	milvus	rig::milvus
MongoDB	rig-mongodb	mongodb	rig::mongodb
Neo4j	rig-neo4j	neo4j	rig::neo4j
PostgreSQL	rig-postgres	postgres	rig::postgres
Qdrant	rig-qdrant	qdrant	rig::qdrant
ScyllaDB	rig-scylladb	scylladb	rig::scylladb
SQLite	rig-sqlite	sqlite	rig::sqlite
SurrealDB	rig-surrealdb	surrealdb	rig::surrealdb

rig::memory is available without the memory feature; it contains the core conversation memory traits and in-memory backend re-exported from rig-core. Enabling features = ["memory"] adds reusable history-shaping policy types from the rig-memory companion crate to the same module.

We also have some other associated crates that have additional functionality you may find helpful when using Rig:

• rig-onchain-kit - the Rig Onchain Kit. Intended to make interactions between Solana/EVM and Rig much easier to implement.