fetcher-llm-streaming

Stream language model API responses via Server-Sent Events.

15|4|Updated Aug 23, 2025

Search Tags:#api #llm #streaming #fetch #realtime #sse #eventstream

Ready to run

npx skills add https://github.com/Ahoo-Wang/fetcher --skill fetcher-llm-streaming

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: fetcher-llm-streaming
Source: https://github.com/Ahoo-Wang/fetcher/tree/main/skills/fetcher-llm-streaming
Command: npx skills add https://github.com/Ahoo-Wang/fetcher --skill fetcher-llm-streaming

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @ahoo-wang/fetcher-eventstream, @ahoo-wang/fetcher-openai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill facilitates real-time streaming of language model outputs utilizing Server-Sent Events, enabling instant data transmission during AI interactions.

Core Features & Use Cases

SSE/Streaming Support: Implements server-sent events for seamless, real-time data flow from language models.
Response Prototype Extension: Adds methods to native Response objects for enhanced event stream handling.
Use Case: Efficiently display AI-generated responses token-by-token in chat interfaces, ensuring users see results instantly as they are produced.

Quick Start

Import the fetcher eventstream package to extend Response functionalities, then process streaming responses directly in your AI client code.

Frequently Asked Questions about fetcher-llm-streaming

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

FAQPage Schema

How do I implement real-time LLM token streaming for a chat interface?▼

Real-time LLM token streaming uses Server-Sent Events (SSE) protocols to transmit data instantly. This Skill enables real-time token streaming by adding methods to native Response objects for seamless event stream handling and parsing in chat applications.

What are Server-Sent Events (SSE) and when do I need them for language model APIs?▼

Server-Sent Events (SSE) facilitate real-time data flow from language models. You need SSE for applications like chat interfaces or live data feeds requiring instant user updates, ensuring results display token-by-token as they are produced.

How to parse event streams from a fetch Response object?▼

To parse event streams from a fetch Response object, import the fetcher eventstream package to extend native Response functionalities. This prototype extension provides mechanisms for direct event stream parsing and response handling in your client code.

Does this SSE streaming approach work with existing fetch API setups?▼

Yes, this SSE streaming approach works with existing fetch API setups by extending the native Response prototype. It adds methods for enhanced event stream handling directly to the Response objects without replacing your current fetch implementation.

What is the best way to terminate a live data feed stream from an LLM?▼

The best way to terminate a live data feed stream is using the provided stream termination mechanisms. This Skill utilizes SSE protocols to offer specific mechanisms for stream termination, ensuring you can stop event parsing safely when needed.