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

Vercel AI SDK community provider for Claude Agent SDK

deep, reliable and confidential coding-context

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

The Rust SDK for building coding agents. Tools, streaming, graph, sub-agent orchestration, MCP — as composable functions

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

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.

The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.

Typed React command-center components, live examples, and a portable coding-agent skill.

Unofficial Go SDK for Claude Code CLI integration. See the Claude Agent SDK documentation for more information. This project has been renamed from claude-code-sdk-go.

OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.

LLM agents as your hyperparameter optimizer.

Rome is the agentic OS.

Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.

Local first, desktop companion platform with animated pets, plugin SDK and coding-agent integrations.

Feedback widget with screenshots, annotations, and AI triage

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

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

🎨 Vibe Design System - Official monday.com UI resources for application development in React.js

Computer-Use SDK for E2E QA Testing

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

Unofficial Ruby SDK for Claude Agent

The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it, with all the best practices already in place.