Awesome Agent Harness

Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.

Visual testing tool for MCP servers

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

Specification and documentation for the Model Context Protocol

The sandbox agent framework.

Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()

A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents

Agentic orchestrator for parallel coding agents — plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

Orchestration layer for coding agents (Claude Code, Codex)

Build and deploy AI Agents on Cloudflare

ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)

Agenta is a workspace where you and your team build agents and automations.

Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.

TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.

AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

Plugins from the Cursor community

A lightweight, powerful framework for multi-agent workflows and voice agents

TinyAGI is the agent teams orchestrator for One Person Company. (fka TinyClaw)

The platform for LLM evaluations and AI agent testing

OpenSource Claude Cowork. A desktop AI assistant that helps you with programming, file management, and any task you can describe.

Laminar - open-source observability platform purpose-built for AI agents. YC S24.

Agent Orchestration Command Center

Headless CLI client for stateful Agent Client Protocol (ACP) sessions

Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents

A framework-agnostic, git-native standard for defining AI agents

OpenLIT is the open-source agent harness engineering platform: trace, evaluate, guard, and improve everything around the model in your AI agents, on OTEL.

Terminal coding agent powered by Kimchi's multi-model orchestration

Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.

Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microsoft docs & code samples.

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

The batteries included agent harness.

The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.

The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers (aka The Norton for OpenClaw)

Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.

Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included

Remote approvals, policy checks, and execution evidence for unattended AI agents.

Universally Triggered Agent Harness - An OpenClaw-like Inngest-powered personal agent