Havuz

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

端到端智能体平台：把本机的 AI Agent 变成人人可用的 Web 产品（Vue 3 + Flask + Go WS 网关 + Docker 部署）

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

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

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

Mercury CLI: multiple AI coding sessions in one terminal. Mix and match provider and locally hosted models, spawn cross-company agents & wor

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

Open Source framework for agentic FileMaker development. Turns SaXML exports into a fast DuckDB-powered digital twin for analysis, documenta

A multi-DAW agent that does literally everything

源码级拆解 DeepSeek Harness · 面向 Agent 开发者的中文学习资料

Unified AI agent integration and automation for Unity Editor.

Compact coding-agent harness built for people who prefer to stay in the terminal

Stock investment and portfolio decision workflows for AI agents: Claude Code, Codex, OpenClaw, DeepSeek Harness (dsh plugin) or your own scr

Framework for building, optimizing, and deploying AI agents as Effect services. Define an agent as a declarative blueprint. Run it against b

A hello-world startup repository for users to help them get started with Agav

Keep it simple, stupid. A highly performant agent harness inspired by Pi, built in Rust.

An agent / harness multiplexer that allows you to access your agents from any device and machine

多智能体应用与任务执行平台

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

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

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

TYSA (Teach Yourself Anything): an learning harness that finds where your understanding ends and teaches from there. Electron app built on M

Forge your own agent harness — a config-to-code generator that renders a thin, standalone Python agent harness you fully own. No LangChain/L

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

OpenPilot — open-source AI 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）

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

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

[NeurIPS 2026] Agentic reinforcement learning for CLI agents with structured action credit assignment, budgeted workspace context selection,

A native desktop coding agent built with Rust and GPUI.

AgenticFlowX is a VS Code workflow layer for AI coding. It gives you chat-first coding, Code / Explore / Spec modes, actionable markdown pre

Build an ETF research agent, one working module at a time. Runnable code, bilingual deep dives, and a traceable 0→1 journey.｜逐模块构建 ETF 投研 Ag

A desktop SQL learning workspace that brings local SQLite, an AI tutor, visual schemas and hands-on practice together through a coordinated

最系统的AI全栈学习实战手册

Private, offline AI coding agent for local Qwen models via Ollama — zero dependencies, real tools, multi-agent. Your code never leaves your

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

Recommend AI coding harness changes from repository context and coding signals, then distribute approved rules, skills, hooks and agents to

내 맥에 상주하는 AI 팀. 텔레그램·슬랙에서 일을 맡기면 누가 담당인지 정하고, 진행이 대시보드에 남습니다.

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

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）

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

For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI

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

A declarative, hermetic harness for Nix-defined agents.

Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter jo

Run your coding agent unattended, and trust the result. A supervision harness for the the agent you already use. Isolated sandbox, durable p

On-device simultaneous interpretation on Apple Silicon — VoxCPM2 on MLX at the core, streaming TTS in ~170 ms, voice clone, any-pair transla

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

Run local LLMs entirely in your browser, with no server, no install and no traces. A private, single-file AI chat UI and AGENT that also wor