Tools for working with OpenAI streams in Node.js and TypeScript.
Tools for working with OpenAI streams in Node.js and TypeScript.
Hooks and components for working with OpenAI streams.
Tools for working with OpenAI streams in Node.js and TypeScript.
Get a stream as a string, Buffer, ArrayBuffer or array
Web Streams, based on the WHATWG spec reference implementation
A tiny (741b) utility for Server Sent Event (SSE) streaming via `fetch` and Web Streams API
An implementation of window.fetch in Node.js using Minipass streams
An iteration of the Node.js core streams with a series of improvements
Merge multiple streams into a unified stream
The string_decoder module from Node core
Tools for working with OpenAI streams in Node.js and TypeScript.
A small fast zlib stream built on [minipass](http://npm.im/minipass) and Node.js's zlib binding.
Turn a readable stream into multiple readable streamx streams
The official TypeScript library for the OpenAI API
Real time OpenAI streams in Node.js and TypeScript.
Streams for reading/writing messages
Open Node Streams on demand.
The **[OpenAI provider](https://ai-sdk.dev/providers/ai-sdk-providers/openai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the OpenAI chat and completion APIs and embedding model support for the OpenAI embeddings API.
A library that makes it easier to work with Streams in the browser.
Tiny utilities for inserting transformation logic into Node.js stream and Web Streams pipelines
Node and Bun local Prisma Streams runtime for trusted development workflows.
TypeScript definitions for ssh2-streams
Codex CLI is a coding agent from OpenAI that runs locally on your computer.
Build LLM clients with ease, attach them to your tools
Provider-neutral Rust SDK for streaming chat and tool calling.
One beautiful Ruby API for GPT, Claude, Gemini, and more. Easily build chatbots, AI agents, RAG applications, and content generators. Features chat (text, images, audio, PDFs), image generation, embeddings, tools (function calling), structured output, Rails integration, and streaming. Works with OpenAI, Anthropic, Google Gemini, AWS Bedrock, DeepSeek, Mistral, Ollama (local models), OpenRouter, Perplexity, GPUStack, and any OpenAI-compatible API. Minimal dependencies - just Faraday, Zeitwerk, and Marcel.
RubyPi is a minimal, composable AI agent harness for Ruby. Build production-ready LLM agents and AI agents with a unified provider interface across OpenAI, Anthropic Claude, and Google Gemini, plus first-class support for tool calling (function calling), streaming responses, automatic retries, provider fallback, context compaction, and a think-act-observe agent loop. Anti-framework design — small, idiomatic, and explicit. Ideal for building autonomous AI agents, ReAct agents, tool-using LLM agents, and chatbots in Ruby.
Streaming SSE client with timeouts/retries; works with NIM/TRT-LLM, vLLM, Ollama, and other OpenAI-style servers.
Ruby-native LLM agent framework with provider adapters (Anthropic, OpenAI, Google), tool calling, streaming, and session persistence.
A unified interface for multiple LLM providers (OpenAI, Anthropic, Google, OpenRouter). Supports streaming, tool calling, and configurable logging.
Intelligence is a lightweight yet powerful Ruby gem that allows you to seamlessly and uniformly interact with large language and vision models (LLM) API's of numerous vendors, including OpenAI, Anthropic, Google, Cerebras, Groq, Hyperbolic, Samba Nova and Together AI. It can be trivially expanded to other OpenAI conformant API providers as well as self hosted models. Intelligence supports text models in streaming and non-streaming mode, vision models, and tool use. Intelligence has minimal dependencies and does not require the vendors ( often bloated ) SDK's.
Swarm is a Ruby library that provides a simple interface for managing OpenAI chat completions with function calling support. It includes features like streaming responses, context management, and function execution.
llm.rb is Ruby's most capable AI runtime. It runs on Ruby's standard library by default. loads optional pieces only when needed, and offers a single runtime for providers, agents, tools, skills, MCP, A2A (Agent2Agent), RAG (vector stores & embeddings), streaming, files, and persisted state. As a bonus, llm.rb is also available for mruby. It supports OpenAI, OpenAI-compatible endpoints, Anthropic, Google Gemini, DeepSeek, xAI, Z.ai, AWS Bedrock, Ollama, and llama.cpp. It also includes built-in ActiveRecord and Sequel support, plus concurrent tool execution through threads, tasks (via async gem), fibers, ractors, and fork (via xchan.rb gem).
PromptWarden provides automatic instrumentation for OpenAI, Anthropic, and Langchain SDKs. Features include policy enforcement, cost calculation, real-time monitoring, and alert recording. Includes CLI tool for live event streaming and comprehensive test coverage.
One beautiful Ruby API for GPT, Claude, Gemini, and more. Easily build chatbots, AI agents, RAG applications, and content generators. Features chat (text, images, audio, PDFs), image generation, embeddings, tools (function calling), structured output, Rails integration, and streaming. Works with OpenAI, Anthropic, Google Gemini, AWS Bedrock, DeepSeek, Mistral, Ollama (local models), OpenRouter, Perplexity, GPUStack, and any OpenAI-compatible API. Minimal dependencies - just Faraday, Zeitwerk, and Marcel.
One beautiful Ruby API for GPT, Claude, Gemini, and more. Easily build chatbots, AI agents, RAG applications, and content generators. Features chat (text, images, audio, PDFs), image generation, embeddings, tools (function calling), structured output, Rails integration, and streaming. Works with OpenAI, Anthropic, Google Gemini, AWS Bedrock, DeepSeek, Mistral, Ollama (local models), OpenRouter, Perplexity, GPUStack, and any OpenAI-compatible API. Minimal dependencies - just Faraday, Zeitwerk, and Marcel. With additional features from the community.
Automatically intercept and log LLM requests from Ruby applications. Supports OpenAI, official Anthropic gem, ruby-anthropic gem, and other Faraday-based libraries. Features dual interceptor architecture, streaming support, thread-safe operation, and automatic duplicate request prevention.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.