Stream Agent filters for GraphAI.
Connect http/websockets client using arbitrary duplex stream
Turn a function into an `http.Agent` instance
HelloAgent SDK — talk to the HelloAgent relay from Node or the browser. Pair, send, receive, and stream agent messages over a single WebSocket.
Node.js Streams, a user-land copy of the stream library from Node.js
Check if something is a Node.js stream
Get a stream as a string, Buffer, ArrayBuffer or array
Toggle the CLI cursor
tar-stream is a streaming tar parser and generator and nothing else. It operates purely using streams which means you can easily extract/parse tarballs without ever hitting the file system.
destroy a stream if possible
Call a callback when a readable/writable/duplex stream has completed or failed.
A streaming way to send data to a Node.js Worker Thread
Get and validate the raw body of a readable stream.
A stream that emits multiple other streams one after another.
Returns the next buffer/object in a stream's readable queue
Streaming data for JavaScript
Merge multiple streams into a unified stream
A tiny, zero-dependency yet spec-compliant asynchronous iterator polyfill/ponyfill for ReadableStreams.
An iteration of the Node.js core streams with a series of improvements
Streaming HTML parser with scripting support.
Azure AI Agents client library.
A micro-library of stream components for building custom JSON and JSONC processing pipelines with a minimal memory footprint — parse, filter, and transform JSON far larger than available memory with a SAX-inspired token API, on Node.js or Web Streams.
minimal implementation of a PassThrough stream
writable stream that concatenates strings or binary data and calls a callback with the result
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.
VSM is a small Ruby framework for building agentic systems using a Viable System Model–style architecture. It gives you Capsules: self‑contained components composed of five named systems (Operations, Coordination, Intelligence, Governance, Identity) plus an async runtime so many capsules can run concurrently.
A Ruby CLI agent runtime with streaming provider adapters.
Ruby-native LLM agent framework with provider adapters (Anthropic, OpenAI, Google), tool calling, streaming, and session persistence.
Rack app exposing the Brute agent over HTTP with JSON and SSE streaming endpoints. Deploy with Falcon.
Cognitive narrative stream for brain-modeled agentic AI
A simple Ruby implementation of the Agent Communication Protocol (ACP) - an open protocol for communication between AI agents, applications, and humans. Supports multimodal messages, real-time streaming, agent discovery, and stateful sessions.
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.
A Ruby port of Google's A2UI (Agent-to-User Interface) for Rails. Uses DSPy.rb to generate typed UI descriptions from natural language, rendered as ViewComponents via Turbo Streams.
SolidAgent extends ActiveAgent with database-backed prompt context management, declarative tool schemas, and real-time streaming updates. Provides has_context, has_tools, and streams_tool_updates concerns for building robust AI agents.
Rubagent is a lightweight Ruby framework for building modular, composable AI agents that can interact with LLMs (like OpenAI), tools, and external APIs. It provides a flexible architecture for defining agents, managing prompts, and orchestrating multi-step workflows using functional patterns. Features: - Streamed LLM responses (OpenAI, etc.) - Plug-and-play agent design - Shared context and memory flow - Support for custom tools and HTTP integrations - Built-in dry-rb and Zeitwerk compatibility
REST + SSE HTTP wrapper for claude-agent-sdk. Exposes Claude Code as a network service with session management, streaming, and authentication.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.