0xPlaygrounds

rig: Build LLM Applications in Rust

Rig is a Rust library for building modular LLM applications, with shared interfaces for model providers, vector stores, and agent workflows. It suits Rust developers who want to integrate multiple LLM services without building each integration from scratch.

View on GitHub Compare
Stars
8.8k
Forks
989
Stars, last 30 days
+259

Our take

Health score

78/100

How it is scored
Activity
90
Community
88
Issues
56
Pull requests
76

+259 stars in the last 30 days

  • Releases more often than 93% of the projects we track
  • Merges more pull requests than 81% of the projects we track
  • More contributors than 78% of the projects we track

Project history

Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.

Selected snapshot

Stars

9,170

Forks

1,024

Change since Nov 17, 2026: +7 stars·+1 forks

Overview

Rig provides Rust building blocks for applications that use large language models. It aims to reduce the integration work involved in combining model providers, embeddings, agent workflows, and vector stores behind a consistent interface.

The project is a fit for teams building LLM features in Rust that want provider flexibility and composable components. Its root rig crate offers a facade over core abstractions and optional companion integrations. See the repository README and documentation for details.

Key Features

  • Unified interfaces for more than 20 model providers and more than 10 vector store integrations.
  • Agent workflows with multi-turn prompting and streaming.
  • Completion and embedding workflows, plus support for transcription and audio and image generation capabilities.
  • Portable core contracts separated from agent orchestration.
  • Optional integrations exposed through Cargo features.
  • Browser-WASM support for the portable core and classic runtime.
  • Cassette utilities for recording and replaying effects, with optional agent and ECS adapters.

Use Cases

  • Rust application developers adding LLM-powered features while keeping provider integrations interchangeable.
  • Teams building tool-using or multi-turn agents that need prompting and streaming workflows.
  • Developers adding semantic search or retrieval with one of the supported vector store integrations.
  • Rust projects that need to combine model completions, embeddings, or supported audio and image capabilities.

Getting Started

Add the facade crate with Cargo:

cargo add rig

For setup and examples, see the README and Rig documentation.

Alternatives

  • AgentsKit: AgentsKit offers a modular JavaScript agent toolkit with runtime, UI, memory, and RAG, while Rig provides Rust interfaces to LLM providers and vector stores.
  • deepagents: Deep Agents is a Python harness with built-in planning, delegation, and file access, while Rig is a Rust library for assembling applications across model providers and vector stores.
ProjectLanguageLicenseStarsStatus
rigRustMIT8.8kNot checked yet
agentskitTypeScriptMIT38Active
deepagentsPythonMIT29.9kActive

Considerations

  • The README warns that upcoming changes may be breaking, so check release notes and migration guidance before upgrading.
  • Provider use requires configuring the credentials and runtime or transport appropriate to the chosen integration. The example uses an OpenAI API key and Tokio.
  • WASM support is limited to the portable core and classic runtime; the README states that WASI is unsupported and rig-rmcp/MCP is native-only.

Found this useful?

Share it with someone who would like rig.

Comparisons