Multi-Agent Harness for Production AI

Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.

GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.

Data context layer for unstructured data - images, video, sensor data, text and PDFs

A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.

DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.

🐉 Dante Cloud 国内首个支持阻塞式和响应式服务并行的微服务云原生基座。采用领域驱动模型(DDD)设计思想，以「高质量代码、低安全漏洞」为核心，高度模块化和组件化设计，支持IoT等物联网设备认证，满足国家三级等保要求、支持接口国密数字信封加解密等系列安全体系的多租户微服务解决方案。独创的“一套代码实现微服务和单体两种架构灵活切换”的企业级微服务平台。🔝🔝 点个star 持续关注更新！

用AI创作高质量内容，小红书版Openclaw，自媒体创作者的AI工作台，小红书创作AI工具RedClaw，支持小红书图文下载、创作风格学习、智囊团AI群聊、小红书AI创作，AI图文制作，AI文章排版｜🌟 Star if you like it! ｜ 你桌面盒子里的AI小河狸🦫

Reference code for the Meta-Harness paper.

Open-source agentic data engineering harness for dbt, SQL, and cloud warehouses. 100+ tools, 10 warehouses, AI-powered.

KWeaver Core is a harness-first foundation for enterprise decision agents. It turns fragmented data, knowledge, tools, and policies into governed context, safe execution, and verifiable feedback loops. With semantic modeling, real-time access, runtime control, and TraceAI, it helps AI systems reason, adapt, and act reliable in complex enterprises.

A general, evolvable, and distributed agent framework & harness for data science.

AI agent tutorials for backend developers without AI background. 适合后端工程师的零基础 AI Agent 教程

🤖 Official Interactive Tutorial for OpenHarness – Zero to Hero in 12 Chapters | Learn OpenHarness like Claude Code: Agent Loop, Tools, Memory, Multi-Agent | 面向零基础的 AI Agent 交互式教程

AutoHarness: Automated Harness Engineering for AI Agents

Agent skill for harness engineering — memory, permissions, context engineering, multi-agent coordination. Distilled from Claude Code, with Codex CLI and Gemini CLI on the roadmap. EN/ZH. Install via npx skills add.

An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.

A ReAct-Based Highly Robust Autonomous Agent (Harness) Framework.

Unified Emacs interface supporting OpenAI Codex, GitHub Copilot CLI, Claude Code, Gemini CLI, Opencode, and more