Existing multi-agent software development systems have proposed many forms of agent collaboration, including role-based collaboration and automated code review. However, many systems assume a common runtime, a central conversation server, or the same API family. Under these assumptions, LLM agents from different vendors cannot easily exchange messages directly from their own execution environments while dividing development and review work on a shared codebase. This paper presents tap, a file-based collaboration protocol that allows Claude (Anthropic) and Codex (OpenAI) to collaborate on one codebase without shared memory or an identical runtime. The core of tap is a file-first design that preserves markdown files with metadata as original messages, combines a file inspection path (file communication, Tier 1) with real-time notification paths for Claude and Codex (real-time communication, Tier 2), and isolates work through separate git worktrees. Even if real-time notification fails or a receiver restarts, the message file remains available and the same content can be inspected again. In a 27-day, 37-generation self-applied operation where tap was used to develop and review itself, we collected 209 tap-related pull requests and 717 operational artifacts. An analysis of 375 review artifacts showed that the share of reviews recording at least one defect or requested change was 69.8% for heterogeneous model pairs and 53.1% for homogeneous model pairs. These results show that tap, which combines file-based message preservation with real-time notification, operates in a real production repository, and that combining heterogeneous models and execution environments can broaden review perspectives. tap is distributed as the open-source npm package @hua-labs/tap (v0.5.2).

翻译：摘要：现有多智能体软件开发系统提出了多种智能体协作形式，包括基于角色的协作及自动化代码审查。然而，许多系统假设存在公共运行时、中央对话服务器或同一API族。在此假设下，来自不同供应商的大语言模型智能体无法在其各自执行环境中直接交换消息，同时在同一共享代码库上划分开发与审查工作。本文提出tap——一种基于文件的协作协议，允许Claude（Anthropic）与Codex（OpenAI）在无需共享内存或相同运行时的条件下协作于同一代码库。tap的核心是"文件优先"设计：将含元数据的Markdown文件作为原始消息保存，结合文件检查路径（文件通信，第1层）与面向Claude和Codex的实时通知路径（实时通信，第2层），并通过独立git工作树隔离任务。即使实时通知失败或接收端重启，消息文件仍可访问，同一内容亦可重新检查。在27天、37次自我迭代的应用中（tap被用于开发并审查自身），我们收集了209个与tap相关的拉取请求及717份操作工件。对375份审查工件的分析显示，记录至少一个缺陷或请求变更的审查比例在异构模型对中为69.8%，在同构模型对中为53.1%。结果表明，结合基于文件的消息保留与实时通知的tap能够在实际生产仓库中运行，且异构模型与执行环境的组合可拓展审查视角。tap以开源npm包@hua-labs/tap（v0.5.2）形式分发。