sage-llm-integration

Orchestrate multiple LLM providers through a unified Sage client with streaming and fallback.

12|1|Updated Jul 15, 2025

Search Tags:#automation #llm #streaming #fallback #provider #client #multiprovider

Ready to run

npx skills add https://github.com/majiayu000/sage --skill sage-llm-integration

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sage-llm-integration
Source: https://github.com/majiayu000/sage/tree/main/.sage/skills/sage-llm-integration
Command: npx skills add https://github.com/majiayu000/sage --skill sage-llm-integration

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a unified Sage LLM client that coordinates multiple providers, enabling streaming responses, rate limiting, and cross-provider fallbacks for robust, code-oriented AI workflows.

Core Features & Use Cases

Unified LlmClient across OpenAI, Anthropic, Google, Azure, Ollama, Doubao, GLM, and more.
Streaming support with SSE and incremental token delivery.
Built-in rate limiting and per-provider configuration to prevent quota exhaustion.
Cross-provider fallback to maintain availability during outages or latency spikes.
Extensible provider architecture for adding new providers with minimal changes.

Quick Start

Configure Sage LLM integration and run a sample chat task across multiple providers; for example, request a code explanation with streaming enabled until completion.

Frequently Asked Questions about sage-llm-integration

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

FAQPage Schema

How do I use a single LLM client across multiple providers like OpenAI and Anthropic?▼

A unified LLM client orchestrates multiple providers through a single interface, enabling consistent chat interactions across OpenAI, Anthropic, Google, Azure, Ollama, Doubao, and GLM without changing code logic.

What is cross-provider fallback and how does it handle LLM outages?▼

Cross-provider fallback maintains service availability by automatically switching to an alternate LLM provider during outages or latency spikes, ensuring robust and uninterrupted AI workflows.

Can I stream LLM responses with SSE and incremental token delivery?▼

Yes, streaming support with Server-Sent Events (SSE) delivers incremental tokens during generation. This allows real-time response rendering for interactive chat across configured providers.

How do I prevent LLM quota exhaustion when automating requests?▼

Built-in rate limiting applies per-provider configuration to throttle automated requests, preventing quota exhaustion and managing traffic flow across the unified multi-provider LLM client.

How do I add a new custom LLM provider to a multiprovider client?▼

An extensible provider architecture allows adding new LLM providers with minimal code changes by implementing the unified provider interface, integrating seamlessly into the existing fallback and streaming mechanisms.