ravi-architecture

Document the Ravi multi-agent runtime architecture and message processing lifecycle.

6|2|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/filipexyz/ravi --skill ravi-architecture
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ravi-architecture
Source: https://github.com/filipexyz/ravi/tree/main/src/plugins/internal/ravi-dev/skills/architecture
Command: npx skills add https://github.com/filipexyz/ravi --skill ravi-architecture

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a comprehensive architectural map of the Ravi runtime, helping developers understand, debug, and extend the multi-agent operating system without getting lost in its complex event-driven infrastructure.

Core Features & Use Cases

  • System Navigation: Provides a clear breakdown of the message flow from Omni channels through NATS JetStream to provider execution.
  • Component Guidance: Offers specific rules for modifying core modules like the session dispatcher, runtime request builder, and host services.
  • Use Case: When onboarding to the codebase or debugging a message routing failure, use this Skill to identify exactly which layer (Omni, Ravi, or Provider) is responsible for the current state.

Quick Start

Use the ravi-architecture skill to explain the message flow from an incoming WhatsApp prompt to the final provider response.

Frequently Asked Questions about ravi-architecture

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

FAQPage Schema
How does multi-agent runtime message routing work in a NATS event-driven architecture?

Multi-agent runtime message routing in a NATS event-driven architecture routes incoming prompts from Omni channels through NATS JetStream to the provider execution layer. The Ravi architecture maps this flow to help developers trace messages across the session dispatcher and runtime request builder.

How do I debug message routing failures in a TypeScript multi-agent runtime?

To debug message routing failures in a TypeScript multi-agent runtime, identify whether the failure originates in the Omni transport, NATS event handling, or provider-specific adapters. The Ravi architecture defines strict boundaries between these layers to isolate issues during system debugging.

How do I extend the session dispatcher and runtime request builder in a multi-agent operating system?

Extending the session dispatcher and runtime request builder in a multi-agent operating system requires following specific rules for modifying core modules. The Ravi architecture provides component guidance to ensure extensions maintain defined boundaries between Omni transport, NATS event handling, and provider adapters.

What is the message flow from an incoming WhatsApp prompt to a provider response in a multi-agent runtime?

The message flow from an incoming WhatsApp prompt to a provider response in a multi-agent runtime passes from Omni channels through NATS JetStream to provider-specific adapters. The Ravi architecture explains this lifecycle to facilitate developer onboarding and system navigation.

When should I use NATS JetStream vs other event handling layers for multi-agent runtime message processing?

NATS JetStream is used for multi-agent runtime message processing when you need reliable event handling between the Omni transport and provider-specific adapters. The Ravi architecture enforces these boundaries, ensuring NATS handles event routing while providers manage execution.

What are the limitations of modifying provider-specific adapters in a multi-agent runtime architecture?

Modifying provider-specific adapters in a multi-agent runtime architecture requires adhering to defined boundaries between the Omni transport, Ravi core, and provider layers. The Ravi architecture warns that crossing these boundaries during component extension can disrupt message processing lifecycle integrity.