rig

Build type-safe LLM applications in Rust with modular agents and tool calling.

3|Updated Jan 10, 2026
One-click install
npx skills add https://github.com/yankeeinlondon/rusty-biscuit --skill rig-yankeeinlondon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rig
Source: https://github.com/yankeeinlondon/rusty-biscuit/tree/main/.claude/skills/rig
Command: npx skills add https://github.com/yankeeinlondon/rusty-biscuit --skill rig-yankeeinlondon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Rig provides a comprehensive, type-safe foundation for building robust, deterministic LLM-powered applications in Rust, enabling reliable tool calling, agent orchestration, and seamless integration with vector stores and multiple providers.

Core Features & Use Cases

  • Tool calling with schema-driven, type-safe definitions for reliable LLM-Tool interactions
  • Modular agent orchestration to compose complex workflows across multiple tools
  • Retrieval-Augmented Generation (RAG) with vector stores and embeddings
  • Multi-provider support and extensible provider architecture for OpenAI-compatible APIs

Quick Start

Install the Rig ecosystem, create a client, build an agent, and prompt it to perform a multi-tool workflow.

Frequently Asked Questions about rig

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build type-safe LLM agents in Rust?

Build type-safe LLM agents in Rust by implementing a trait-driven architecture with schema-driven tool definitions and modular agent orchestration to compose complex, deterministic workflows.

How do I implement tool calling in a Rust LLM application?

Implement tool calling in a Rust LLM application using schema-driven, type-safe definitions for tool interactions. This ensures reliable execution when the LLM agent invokes external functions.

Can I use Rust for Retrieval-Augmented Generation with vector stores?

Use Rust for Retrieval-Augmented Generation by integrating vector stores and embedding models. This allows you to store and retrieve contextual data for dynamic LLM prompts.

Does this Rust LLM framework support OpenAI-compatible APIs?

Yes, the framework supports OpenAI-compatible APIs through its multi-provider architecture. This extensible design allows you to connect to various LLM providers seamlessly.

What is the best way to orchestrate multiple LLM tools in Rust?

Orchestrate multiple LLM tools in Rust using modular agent composition. This approach allows you to build complex workflows across multiple tools deterministically.

Why use a trait-driven architecture for Rust LLM apps?

Use a trait-driven architecture for Rust LLM apps to enforce type safety across tool definitions, embedding models, and vector stores, ensuring robust and deterministic task execution.