Zero-token orchestrator for the Agentic Coding Protocol — state machine, rules table, dispatch logic, CC integration
Server & Client SDK for Agent2Agent protocol
The Agent Client Protocol (ACP) is a protocol that standardizes communication between *code editors* (interactive programs for viewing and editing source code) and *coding agents* (programs that use generative AI to autonomously modify code).
Playwright Tools for MCP
GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.
Lightdash CLI tool
Cloud and zero-trust agentic workflow marketplace for skills, agents, rules, MCP references, and compliance-aware architecture.
The **Model Context Protocol (MCP) client** for the [AI SDK](https://ai-sdk.dev/docs) lets you connect to MCP servers and use their tools with AI SDK functions like `generateText` and `streamText`.
The Agent Client Protocol (ACP) is a protocol that standardizes communication between *code editors* (interactive programs for viewing and editing source code) and *coding agents* (programs that use generative AI to autonomously modify code).
Dual-protocol payment infrastructure for autonomous AI commerce (AP2 + ACP)
1,508+ agentic skills for Claude Code, Gemini CLI, Cursor, Antigravity & more. Installer CLI.
Playwright CLI
MCP server for SAPUI5/OpenUI5 development
Hud's Node SDK
Opinionated chat agent with agentic loop, stream resumption, client tools, and extensions
Forge - a local-first, multi-agent, programmable software-engineering runtime
Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory persistence, GitHub integration,
ACP agent in TypeScript that uses the Zhipu AI GLM series (specifically GLM-5.1 and GLM-4.7) as the reasoning core
Agentic Quality Engineering V3 - Domain-Driven Design Architecture with 13 Bounded Contexts, O(log n) coverage analysis, ReasoningBank learning, 60 specialized QE agents, mathematical Coherence verification, deep Claude Flow integration
Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you.
The postgres client/server binary protocol, implemented in TypeScript
Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.
The Chrome DevTools Protocol JSON
Ultra-fast code editing engine - 52x faster than Morph LLM at $0 cost
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.
A Model Context Protocol (MCP) server that enables AI agents to query information about gems in a Ruby project's Gemfile, including source code and metadata.
Claude Swarm enables you to run multiple Claude Code instances that communicate with each other via MCP (Model Context Protocol). Create AI development teams where each instance has specialized roles, tools, and directory contexts. Define your swarm topology in simple YAML and let Claude instances collaborate across codebases. Perfect for complex projects requiring specialized AI agents for frontend, backend, testing, DevOps, or research tasks.
Ruby client for `@earendil-works/pi-coding-agent`. Spawns the pi CLI in RPC mode and speaks its JSONL protocol from Ruby. Designed for building interactive agent UIs (web, TUI) on top of pi. Not officially maintained by the pi project.
An MCP (Model Context Protocol) server that provides LLM agents with access to runtime context of executing Ruby processes. Connect to debug sessions, evaluate code, inspect objects, and control execution flow via MCP tools.
Rails Active MCP enables secure Rails console access through Model Context Protocol (MCP) for AI agents and development tools like Claude Desktop. Provides safe database querying, model introspection, and code execution with comprehensive safety checks and audit logging. Features include: • Safe Ruby code execution with configurable safety checks • Read-only database query tools with result limiting • Rails model introspection (schema, associations, validations) • Dry-run code analysis for safety validation • Environment-specific configuration presets • Comprehensive audit logging and monitoring • Claude Desktop integration out of the box
pikuri-core is the lean, audit-friendly foundation of the pikuri family: Pikuri::Agent (a thin wrapper around ruby_llm's chat loop) with its Configurator + Extension protocol, the strict Pikuri::Tool framework, a listener surface for rendering / budgets / sub-agents, and four bundled stateless tools (calculator, web search, web scrape, fetch). Extensions (skills, MCP, workspace, coding stack, named-agent personas) live in sibling gems so a privacy-conscious user can install just this core and audit a minimal dependency tree. For the convenience bundle that pulls in everything, see the +pikuri+ metagem.