TTal – 将 Claude Code 转化为多智能体软件工厂的 CLI 工具
2 分•作者: neilbb•3 天前
我构建 TTal 是因为我厌倦了照看 Claude Code 会话。每次 PR 都意味着需要在窗口之间切换，复制粘贴审查反馈，告诉程序员需要修复什么，然后重复这个过程直到合并。我希望能够在做其他事情的同时，通过手机来管理这一切。
TTal 是一个 Go CLI 工具，它在两层架构中编排多个 Claude Code 会话：
* **管理层** — 长期运行的代理，在会话之间保持持久。它们起草计划，将其分解成任务，分配优先级，并在工作者遇到问题时为其解除阻塞。您可以通过 Telegram 管理它们。
* **工作层** — 每个任务都会生成短期的代理。每个代理都会获得一个隔离的 git 工作树 + tmux 会话。它们实现、审查、处理反馈和合并——完整的 PR 循环在 CI 日志反馈的情况下自主运行。完成后，一切都会自动清理。
代理、工作者和人类都通过一个 p2p 消息桥进行通信——任何代理都可以直接向任何其他代理或人类发送消息。
我遇到的另一个问题是：我需要专用的、长期运行的 Claude Code 代理来进行规划和研究——而不仅仅是临时的编码会话。TTal 的管理层为我提供了这一点。我的编排代理起草计划，我的研究员探索代码库，而工作者只需执行。
该技术栈是有意可组合的——使用 taskwarrior 进行任务管理，使用 flicknote 或纯 markdown 进行知识/记忆，Telegram 作为人机交互界面。一切都通过 CLI 进行通信，无需 SDK。
```
brew tap tta-lab/ttal
brew install ttal
```
GitHub: https://github.com/tta-lab/ttal-cli
我还构建了一个仅限 bash 的子代理运行时，零工具调用开销：https://github.com/tta-lab/logos
很乐意回答有关架构或多代理工作流程的任何问题。
查看原文
I built TTal because I got tired of babysitting Claude Code sessions. Every PR meant switching between windows, copy-pasting review feedback, telling the coder what to fix, and repeating until it merged. I wanted to manage all of this from my phone while doing other things.<p>TTal is a Go CLI that orchestrates multiple Claude Code sessions in a two-plane architecture:<p>Manager plane — long-running agents that persist across sessions. They draft plans, break them into tasks, assign priorities, and unblock workers when they get stuck. You manage them from Telegram.<p>Worker plane — short-lived agents spawned per task. Each gets an isolated git worktree + tmux session. They implement, review, triage feedback, and merge — the full PR loop runs autonomously with CI logs fed back in. When done, everything auto-cleans up.<p>Agents, workers, and humans all communicate through a p2p message bridge — any agent can message any other agent or the human directly.<p>The other problem I had: I needed dedicated, long-lived Claude Code agents for planning and research — not just throwaway coding sessions. TTal's manager plane gives me that. My orchestrator agent drafts plans, my researcher explores codebases, and workers just execute.<p>The stack is intentionally composable — taskwarrior for task management, flicknote or use plain markdown for knowledge/memory, Telegram as the human-in-the-loop interface. Everything talks via CLI, no SDK required.<p><pre><code> brew tap tta-lab/ttal
brew install ttal
</code></pre>
GitHub: https://github.com/tta-lab/ttal-cli<p>I also built a bash-only subagent runtime with zero tool call overhead: https://github.com/tta-lab/logos<p>Happy to answer questions about the architecture or multi-agent workflows in general.