Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

rig

rig: A Rust library for building modular and scalable applications on large language models.

What problem it solves

Building LLM applications often requires connecting model providers, vector stores, tools, streaming, and agent capabilities. Rig provides a shared Rust interface for these components and includes a terminal coding agent that can be extended with plugins.

Key features

  • Unified model and vector-store interfaces — Use a shared interface for model providers and vector stores, with support for completion, embedding, transcription, audio, and image models.

    Source: README

  • Agents with tools and streaming — Construct agents with preambles and tools, send prompts asynchronously, and work with streaming responses and typed hooks.

    Source: README

  • Feature-based crate selection — Select capabilities through Cargo features, including memory, local embeddings, saved conversations, record-and-replay support, and MCP tools.

    Source: README

  • Extensible terminal coding agent — The terminal agent organizes tools, commands, sessions, sign-in, and the terminal view as replaceable or optional plugins. Changes can be rebuilt while retaining the active session.

    Source: README

  • Browser and native targets — The core library and agent crate support browser WebAssembly builds, while the terminal agent runs on Linux and macOS.

    Source: README

Quick start

Copied verbatim from the project's README.

cargo add rig anyhow
cargo add tokio --features macros,rt-multi-thread
use rig::prelude::*;
use rig::providers::openai::{self, OpenAI};

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    // Reads OPENAI_API_KEY.
    let model = OpenAI::from_env()?.completion(openai::GPT_6_2_SOL);
    let agent = AgentBuilder::new(model)
        .preamble("You are a comedian.")
        .build();

    let response = agent.prompt("Entertain me!").await?;
    println!("{}", response.output());
    Ok(())
}

Who it may suit

This may suit Rust developers building LLM-powered applications or extending the terminal coding agent with custom plugins.

Topics to discuss

  • Which provider and vector-store integrations should receive priority next?

  • What plugin capabilities would be most useful for the terminal coding agent?

  • How should examples and guides cover agent tools, streaming, and typed hooks?


Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/0xPlaygrounds/rig#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/0xPlaygrounds/rig

Comments

…