Launch coding agents (CLI tools, editors, or web agents) with a prompt
Open-source Agent SDK. Runs the full agent loop in-process — no local CLI required. Deploy anywhere: cloud, serverless, Docker, CI/CD.
An HTTP(s) proxy `http.Agent` implementation for HTTPS
A SOCKS proxy `http.Agent` implementation for HTTP and HTTPS
A light-weight module that brings Fetch API to node.js
Turn a function into an `http.Agent` instance
Open Policy Agent WebAssembly SDK
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-node) [](https://www.npmjs.com/
Maps proxy protocols to `http.Agent` implementations
The open agent skills ecosystem
[](https://www.npmjs.com/package/@aws-sdk/middleware-user-agent) [](https://www.npmjs.c
New Relic agent
Skillflag producer CLI reference implementation.
Get a user agent string across all JavaScript Runtime Environments
Agent-native CLI for AI mobile testing and app automation across iOS, Android, tvOS, Android TV, macOS, and Linux.
New Relic Browser Agent
A module for generating metrics from V8.
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-browser) [](https://www.n
An HTTP(s) proxy `http.Agent` implementation for HTTP
An ACP-compatible coding agent powered by Codex
NodeJS http(s) agent implementation for VS Code
Codex CLI is a coding agent from OpenAI that runs locally on your computer.
HTTP proxy tunneling agent. Formerly part of mikeal/request, now a standalone module.
XMLHttpRequest for Node
OpenCode provider for Nucel agent-sdk — HTTP client to OpenCode server
Universal API for automatic coding agents in sandboxes. Supports Claude Code, Codex, OpenCode, and Amp.
Universal API for automatic coding agents in sandboxes. Supports Claude Code, Codex, OpenCode, and Amp.
Universal API for automatic coding agents in sandboxes. Supports Claude Code, Codex, OpenCode, and Amp.
OpenClacky is a 100% open-source (MIT) AI Agent that matches Claude Code on capability at comparable cost. Built on two years of agentic R&D, it ships with a minimal 16-tool core, near-100% prompt cache hit rate, idle-time auto-compression, and BYOK support for any OpenAI-compatible model. A natural-language Skill system lets you create, evolve, and monetize agent capabilities without writing code, plus first-class integrations with Feishu, WeCom, WeChat, Discord, and Telegram.
Create, manage, and distribute reusable skills for AI agents.
LlamaBotRails is a gem that turns your existing Rails App into an AI Agent by connecting it to an open source LangGraph agent, LlamaBot.
Rails middleware that authorizes incoming requests against a Policy Decision Point, such as an Open Policy Agent server
Parse, validate, create, package, and load Agent Skills in Ruby. Agent Skills is an open format (by Anthropic) for giving AI agents new capabilities through structured instructions, scripts, and resources.
User agent parser written in Ruby using regex patterns from the Open Podcast Analytics Working Group.
An open protocol enabling communication and interoperability between opaque agentic applications.
Load, validate, and integrate Agent Skills with RubyLLM. Supports the open Agent Skills specification for progressive skill discovery and loading from filesystem, zip archives, and databases.
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.
Agents is a framework for building Multi-Agent Systems (MAS) in Ruby. With support of COPL (Concurrency-Oriented Programming Language - thx to Celluloid) and Neural Nets (thx to ai4r). We have built Agens in order to design Multi-Agent System (MAS) to drive our Probee Open Hardware robot. We wanted to build this MAS in Ruby. Build with love in Prague.
Full-parity Ruby SDK implementing the Agent Client Protocol — a JSON-RPC 2.0 based open protocol for communication between code editors and AI coding agents over stdio.
An open-source, security-first AI agent framework in Ruby with capability-based permissions, sandboxed skills, and a layered prompt system.
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.