Harness engineering beginner tutorial, from 0 to 1

🛠️ Awesome tools & guides for harness engineering.

The all-in-one AI agent living in your terminal. Build landing, mobile apps, backends, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels.

MCP Toolkit for Flutter AI Agent Driven Development (MCP/CLI + custom client side tools) - via closed feedback loop (visual & semantic snapshot) and high client side customization adaptable for any Flutter app. Nowadays it is often called as agentic harness.

Agentic Data Engineering Harness for building data pipelines, data products, data APIs, and data lakes autonomously

Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. Works with any MCP-compatible client.

unified agent workspace

A lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.

AI framework for Ruby/Rails developers

Open-source Environment toolkit of claw-like agents, support task/harness generation and evaluation

A traceable, approval-driven methodology harness for AI pair programming.

A light-weight and straightforward system for spec-driven development with Claude Code or OpenAI Codex

A minimal, composable AI agent harness framework in Python.

BoringOS is the open-source operating system for AI agents - it ships with a shell portal plus installable modules, powered by agentic CLIs.

论文解析 Agent 系统（Agent Harness + Loop Engineering），实现结构化抽取与闭环验证优化。

Local harness substrate for project-scoped agent sessions.

A TypeScript-specialized development harness for building reliable, polished, modern web apps.

Ostrom-compliant commons governance & development system for AI agents to assist building products from requirements to production & deployment.

AMP (Agent Mailer Protocol) is an async mailbox system for AI agents. Instead of chaining tools, writing DAGs, or building RPC glue — agents just send messages to each other. Works with Claude Code, Codex, Cursor, OpenClaw and any custom agents. Designed for real-world, long-running, iterative coding workflows

Let's Qitos! A torch-like agent-native framework for researchers.