Rig – Agentic Workflows in Rust

Rig, a Rust library for building LLM-powered applications, has been released with support for agentic workflows, multi-turn streaming, and 20+ model providers under a unified interface. The library, developed by 0xPlaygrounds, includes a classic agent runtime, 10+ vector store integrations, and browser-WASM support, with users including St. Jude, Coral Protocol, and Nethermind.

📑 Docs https://rig.rs/docs • 🌐 Website https://rig.rs • 🤝 Contribute https://github.com/0xPlaygrounds/rig/issues/new • ✍🏽 Blogs https://rig.rs/docs/guides • ✨ 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. 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 https://rig.rs/docs and crate https://docs.rs/rig/latest/rig/ API reference documentation. - Agentic workflows that can handle multi-turn streaming and prompting - A classic agent runtime enabled by default - Full GenAI Semantic Convention https://opentelemetry.io/docs/specs/semconv/gen-ai/ 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 - Browser-WASM wasm32-unknown-unknown support for the portable core and classic runtime — see target support /0xPlaygrounds/rig/blob/main/crates/rig-agent/README.md target-support for the full matrix WASI is not supported; rig-rmcp /MCP is native-only 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 . Below is a non-exhaustive list of companies and people who are using Rig: St Jude https://www.stjude.org/ - Using Rig for a chatbot utility as part of, a genomics visualisation tool. proteinpaint Coral Protocol https://www.coralprotocol.org/ - Using Rig extensively, both internally as well as part of the Coral Rust SDK. https://github.com/Coral-Protocol/coral-rs VT Code https://github.com/vinhnx/vtcode - 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 https://github.com/nowledge-co/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 https://dria.co/ - a decentralised AI network. Currently using Rig as part of their compute node. https://github.com/firstbatchxyz/dkn-compute-node Nethermind https://www.nethermind.io/ - Using Rig as part of their Neural Interconnected Nodes Engine https://github.com/NethermindEth/nine framework. Neon https://neon.com - Using Rig for their app.build https://github.com/neondatabase/appdotbuild-agent V2 reboot in Rust. Listen https://github.com/piotrostr/listen - A framework aiming to become the go-to framework for AI portfolio management agents. Powers the Listen app. https://app.listen-rs.com/ Cairnify https://cairnify.com/ - 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 https://ryzome.ai - 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 https://github.com/sopaco/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 https://github.com/sopaco/cortex-mem - 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 https://github.com/nearai/ironclaw - A secure personal AI assistant ilert https://www.ilert.com/ - Incident management & alerting platform. Uses Rig as the multi-provider abstraction in its agentic LLM proxy powering ilert AI. Archestra https://github.com/archestra-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 https://github.com/0xPlaygrounds/awesome-rig . Are you also using Rig? Open an issue https://www.github.com/0xPlaygrounds/rig/issues to have your name added 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 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 /0xPlaygrounds/rig/blob/main/examples . Provider-specific integration coverage lives under , with cassette-backed tests that replay offline by default and live-only tests kept separate when real provider APIs are still required. See /0xPlaygrounds/rig/blob/main/tests/providers tests/providers for test target, replay, record, and cassette safety commands. More detailed use case walkthroughs are regularly published on our /0xPlaygrounds/rig/blob/main/tests/README.md tests/README.md Dev.to Blog https://dev.to/0thtachi and added to Rig's official documentation at rig.rs/docs https://rig.rs/docs . 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 rig-s3vectors s3vectors rig::s3vectors rig-candle candle rig::candle rig-vectorize vectorize rig::vectorize rig-fastembed fastembed rig::fastembed rig-gemini-grpc gemini-grpc rig::gemini grpc rig-vertexai vertexai rig::vertexai rig-helixdb helixdb rig::helixdb rig-lancedb lancedb rig::lancedb rig-memory memory rig::memory rig-milvus milvus rig::milvus rig-mongodb mongodb rig::mongodb rig-neo4j neo4j rig::neo4j rig-postgres postgres rig::postgres rig-qdrant qdrant rig::qdrant rig-scylladb scylladb rig::scylladb rig-sqlite sqlite rig::sqlite 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. https://github.com/0xPlaygrounds/rig-onchain-kit Intended to make interactions between Solana/EVM and Rig much easier to implement.