rig

Name: rig
Availability: InStock
Author: yoogo

Build AI applications with a provider-agnostic Rust API for agents and RAG pipelines.

Updated Mar 5, 2026

Search Tags:#llm #rag #agent #streaming #rust #tool-calling #ai-framework

Ready to run

npx skills add https://github.com/yoogoc/xcraw --skill rig-yoogoc

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rig
Source: https://github.com/yoogoc/xcraw/tree/main/.opencode/skills/rig
Command: npx skills add https://github.com/yoogoc/xcraw --skill rig-yoogoc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Rig provides a provider-agnostic Rust framework to rapidly compose and deploy LLM-powered applications, removing the friction of integrating multiple providers and patterns.

Core Features & Use Cases

Unified API across providers for agents, RAG, tool calls, and streaming completions.
Ready-made patterns like Simple Agent, Agent with Tools, and Structured Extraction to accelerate development.
Use case: Build a multi-provider AI assistant that fetches context, calls tools, and streams responses.

Quick Start

Instantiate a Rig client and build a simple agent with a provider to handle a basic prompt.

Frequently Asked Questions about rig

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

FAQPage Schema

How do I build a Rust AI app with a provider-agnostic API?▼

You can build a Rust AI app with a provider-agnostic API by instantiating a client to compose agents, RAG pipelines, and tool-calling workflows. This framework abstracts multiple LLM providers, allowing rapid deployment of unified AI applications.

Can I use Rust to create streaming completions and agents across multiple LLM providers?▼

Yes, you can use Rust to create streaming completions and agents across multiple LLM providers. The framework provides a unified API for building agents, RAG pipelines, and tool-calling workflows that seamlessly operate across different providers.

What's the best way to implement tool-calling workflows and structured extraction in Rust?▼

The best way to implement tool-calling workflows and structured extraction in Rust is using ready-made patterns like Agent with Tools and Structured Extraction. These patterns accelerate development by providing built-in compositions for async tokio operations.

Do I need async tokio patterns and Rust proficiency to use this AI framework?▼

Yes, you need async tokio patterns and Rust proficiency to use this AI framework. Building agents, RAG pipelines, and tool-calling workflows requires experience with agent builders, tools, and optional vector-store integration in async Rust environments.

Does this Rust AI framework support vector-store integration for RAG pipelines?▼

Yes, this Rust AI framework supports optional vector-store integration for RAG pipelines. You can build retrieval-augmented generation pipelines that fetch context, call tools, and stream responses across a unified provider-agnostic API.

How does a provider-agnostic Rust framework handle multi-provider AI assistants?▼

A provider-agnostic Rust framework handles multi-provider AI assistants by offering a unified API that removes integration friction. It allows you to compose agents that fetch context, call tools, and stream responses seamlessly across different LLM providers.