Havuz

A cross-platform agent framework and samples, support on Windows/MacOS/Android/iOS/HarmonyOS

Monitoring & Safety layer for all your agents. Open Source CLI & Skills for Claude Code, Codex, Cursor, Jev and your preferred agents.

基于MAF的Coding Agent智能体

👋 Claude Code & Codex harness insights dashboard — visual catalog and token analytics for skills, agents, plugins, hooks, memory, and more!

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes

Hive Agents harnest agent loop localfirts

A tested harness for durable work across coding agents: CLAUDE.md/CHECKPOINT.md state and 17 skills, a Claude Code plugin with enforcing hoo

A local agent workstation: one Go loop, three doors: Wails desktop, browser, and CLI. It writes code, reviews hunks, opens an isolated brows

从零手搓的 Coding Agent（ReAct + 工具 + 记忆 + 权限 + 上下文压缩 + 子agent + MCP），纯 Python/asyncio

Work less, produce more, Be lazy. The-LazyIDE is the desktop AI IDE built for lazy-smart engineers: a LazyManager who plans and orchestrates

Version-controlled authoring and self-improvement for AGENTS.md

A multi-DAW agent that does literally everything

Git-Native Coding Agent for Mac

A lightweight, general-purpose harness for tool-using LLM agents, fair benchmark evaluation, harness baselines, and personal assistant workf

10,000+ CLI tools. One CLI to access. Zero configuration

All you need is one API to let AI assist you in music creation—modify MIDI files, get suggestions, and more. No complex setup, just plug and

Unofficial Electron desktop shell for DeepSeek Harness: bundled Node runtime, installers, auto-update.

🏗️ AI Agent 九维基础设施框架 - 9个架构维度、11个插件、21个Hooks、30条基准评测

khive is a system of records and operations for agent-native organizations

Evaluate (lint, review, and security-audit) your AI coding agent harness.

Claude Code 非官方开源桌面客户端——接入 SDK 控制协议，权限卡片审批、多模型切换、多 Tab 会话、视频分析（Tauri 2 + React）

Autonomous AI-powered penetration testing platform. LLM-driven recon, vulnerability analysis, and exploit validation for internal & external

a Lua-scriptable experimental coding harness

A one-click installer that scaffolds a complete GitHub Copilot agentic coding environment into any project

Autonomous Personal AI Assistant for office work, exposed as a Model Context Protocol (MCP) server and listed on the Official MCP Registry a

Open-source, model-portable coding agent built for cost-efficient, verifiable software work—with model routing, progressive context, compact

Agent harness research ebook — model-agnostic architecture specification (June 2026)

OpenPilot — open-source AI agent harness

🪢 Local-first, agent-agnostic R&D harness — persistent memory, domain SOPs, contract handoffs & quality gates for PM + Engineering | 本地优先、工具

Simple Long Horizon Agent - A simple yet effective AI agent for learning, experimentation, and long horizon work.

The next easy code and work AI agents harness system: auto, asynchronous, concurrency, efficiently and High accuracy

A unified CLI for Harness. Built for Humans and Agents. Manage pipelines, artifacts, platform resources, and more from the command line.

A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set

使用 DeepSeek 官方多模态视觉模型让你的 Agent 不再眼瞎（支持 DSH、Zed、OpenCode、Codex、Claude Code、Cursor、Claude Desktop）

Distribute and safely manage a cross-host personal harness and durable work state.

A Rust crate to connect multiple harnesses under one, simple, up-to-date interface.

Make Worlds with Code — your coding agent writes procedural three.js scenes, games and objects, screenshots them, and fixes what it sees.

The best AI harness you can run yourself. One file: web UI, tools, memory and orchestration built in. Run a team of agents across providers

多智能体应用与任务执行平台

An AI agent for your desktop and terminal.

An end-to-end framework for Agentic Reinforcement Learning.

An AI chat agent (harness) with integrated tools, skills and an optional knowledge base. Chat with any OpenAI-compatible LLM, use built-in i

A Pi extension command that executes raw user intent to completion with strict, verifiable termination. `/until-done` runs until a truthful

ArchiCode is a graph first chat coding harness where familiar visual flows & nodes are the shared evolving source of truth for both develope

Attention is your scarcest resource. Chief is the local-first layer that guards it — turning every agent, alert, and feed into one honest ca

PTCG-Bench: Can LLM Agents Master Pokémon Trading Card Game? (EMNLP 2026 Findings)

面向中文内容创作者的 AI 写作工作台 | Harness 单层 Agent 编排 · 多源检索 · 风格化写作 · 质量评审 · 分层记忆 · 编辑部多 Agent 协作

free and open source terminal agent harness 🤖

Run your company with AI agents. Open source harness for operating a full company with specialized Claude Code squads.

neural networks in pure C