The official Java SDK for Model Context Protocol servers and clients. Maintained in collaboration with Spring AI

blazigly fast gRPC/MCP client & server implementation in zig

A Model Context Protocol (MCP) client library and debugging toolkit in Rust. This foundation provides both a production-ready SDK for building MCP integrations and the core architecture for an interactive debugger.

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

Go SDK for Anthropic Claude Code CLI – unofficial Claude Code Go agent SDK

Java test automation framework for web, mobile, API, CLI, database, and desktop E2E testing with a fluent API and built-in reporting.

Rails Engine with MCP compliant Spec.

Bug bounty agent framework for Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, and OpenClaw — 48 agents, 26 commands, 19 CLI tools, 2 MCP servers, autonomous hunt loops, exploit chain builder.

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source

Fluent argument validation for fluent software development.

ScaledMCP is a horizontally scalabled MCP and A2A Server. You know, for AI.

A Lisp with first-class LLM primitives, implemented in Rust

C# coding-agent harness (.NET 10, Microsoft Agent Framework) — sessions, tools, permissions, providers, MCP, plugins

Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.

The full-stack TypeScript framework to build, test, and deploy production-ready MCP servers and AI-native apps.

Real time communication for agents. Wake on message, channels, DMs and actions. Useful for orchestrating agents.

A minimal yet powerful framework for creating AI agents with full control over tools, providers, and execution flow.

🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included.