What it does
File-based comms protocol for AI-to-AI dialogue between terminal agents.
- Connects 在你的电脑上运行
- Account or key No key needed · 3 settings to fill in (LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID)
- Category 开发者工具
可搭配使用
教 AI 做这类工作的 Skill,可与本项一起使用
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
为什么排在这里
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 0/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 7/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 7/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
安装
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Letterbox。按照 https://mcp.popnx.com/i/dovahkiin-v-letterbox.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月14日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要填写 3 项设置(LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID) · 需要先在电脑上安装 Python (uv)(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
让 AI 帮你安装
把这段话复制到 Claude 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude 安装 MCP server Letterbox,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "letterbox": { "command": "uvx", "args": [ "letterbox" ], "env": { "LETTERBOX_CHANNEL": "your-value", "LETTERBOX_SENDER": "your-value", "LETTERBOX_INSTANCE_ID": "your-value" } } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID 先保留 "your-value",请我自己把真实值粘贴到文件或应用的输入框里。不要让我在对话里输入密钥。5) 按约定执行,然后确认 Letterbox 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 uv(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --version- 显示版本号(例如 uv …)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
uv --version安装一次,所有需要 uv 的工具都能用
填写 3 项设置
这些是程序设置,不是密钥,无需注册。按开发者的说明填写。
LETTERBOX_CHANNEL要打开的频道名称。通常由 letterbox PTY 父进程在启动此服务器时设置;仅在单独运行 MCP 服务器时才手动设置。查看英文原文
Channel name to open. Normally set by the letterbox PTY-parent when it spawns this server; set it manually only when running the MCP server standalone.LETTERBOX_SENDER此端点在通道上的身份,即对端代理在每条消息中看到的名称。查看英文原文
This endpoint's identity on the channel — the name the peer agent sees on every message.LETTERBOX_INSTANCE_ID每次启动的实例 ID,是 watcher/自写入的关联键,防止代理把自己的消息当作收到的消息。每次启动必须唯一。查看英文原文
Per-launch instance id, the watcher/own-write join key that stops an agent seeing its own messages as incoming. Must be unique per launch.
说明为自动翻译,变量名保持原样;不确定时请查看原文。
打开电脑版 Claude 应用的设置文件
SettingsDeveloperEdit Config
粘贴这些设置并保存文件
{ "mcpServers": { "letterbox": { "command": "uvx", "args": [ "letterbox" ], "env": { "LETTERBOX_CHANNEL": "your-value", "LETTERBOX_SENDER": "your-value", "LETTERBOX_INSTANCE_ID": "your-value" } } } }退出 Claude 再重新打开
试一试
用 Letterbox 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Letterbox,或回答中出现 Letterbox 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Letterbox
Letterbox 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
你可以改用这些方式
A · 使用能连接 Letterbox 的应用
- 需要填写 3 项设置(LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID) · 需要先在电脑上安装 Python (uv)(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
- 需要填写 3 项设置(LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID) · 需要先在电脑上安装 Python (uv)(只需一次)
- 需要填写 3 项设置(LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID) · 需要先在电脑上安装 Python (uv)(只需一次)
- 需要填写 3 项设置(LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID) · 需要先在电脑上安装 Python (uv)(只需一次)
B · 开发者工具 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
- Sentry✓ ChatGPT
- Compiler Explorer✓ ChatGPT
- GitDiagram✓ ChatGPT
可连接 Claude Code,但需要先准备
需要填写 3 项设置(LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID) · 需要先在电脑上安装 Python (uv)(只需一次)
让 AI 帮你安装
把这段话复制到 Claude Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude Code 安装 MCP server Letterbox,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user letterbox --env LETTERBOX_CHANNEL=your-value --env LETTERBOX_SENDER=your-value --env LETTERBOX_INSTANCE_ID=your-value -- uvx letterbox 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID 先保留 "your-value",请我自己把真实值粘贴到文件或应用的输入框里。不要让我在对话里输入密钥。5) 按约定执行,然后确认 Letterbox 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 uv(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --version- 显示版本号(例如 uv …)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
uv --version安装一次,所有需要 uv 的工具都能用
填写 3 项设置
这些是程序设置,不是密钥,无需注册。按开发者的说明填写。
LETTERBOX_CHANNEL要打开的频道名称。通常由 letterbox PTY 父进程在启动此服务器时设置;仅在单独运行 MCP 服务器时才手动设置。查看英文原文
Channel name to open. Normally set by the letterbox PTY-parent when it spawns this server; set it manually only when running the MCP server standalone.LETTERBOX_SENDER此端点在通道上的身份,即对端代理在每条消息中看到的名称。查看英文原文
This endpoint's identity on the channel — the name the peer agent sees on every message.LETTERBOX_INSTANCE_ID每次启动的实例 ID,是 watcher/自写入的关联键,防止代理把自己的消息当作收到的消息。每次启动必须唯一。查看英文原文
Per-launch instance id, the watcher/own-write join key that stops an agent seeing its own messages as incoming. Must be unique per launch.
说明为自动翻译,变量名保持原样;不确定时请查看原文。
打开终端
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add --scope user letterbox --env LETTERBOX_CHANNEL=your-value --env LETTERBOX_SENDER=your-value --env LETTERBOX_INSTANCE_ID=your-value -- uvx letterbox在 Claude Code 中输入 /mcp
应能看到 Letterbox 在列表中并显示已连接
试一试
用 Letterbox 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Letterbox,或回答中出现 Letterbox 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要填写 3 项设置(LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID) · 需要先在电脑上安装 Python (uv)(只需一次)
让 AI 帮你安装
把这段话复制到 Cursor 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Cursor 安装 MCP server Letterbox,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "letterbox": { "command": "uvx", "args": [ "letterbox" ], "env": { "LETTERBOX_CHANNEL": "your-value", "LETTERBOX_SENDER": "your-value", "LETTERBOX_INSTANCE_ID": "your-value" } } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID 先保留 "your-value",请我自己把真实值粘贴到文件或应用的输入框里。不要让我在对话里输入密钥。5) 按约定执行,然后确认 Letterbox 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 uv(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --version- 显示版本号(例如 uv …)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
uv --version安装一次,所有需要 uv 的工具都能用
填写 3 项设置
这些是程序设置,不是密钥,无需注册。按开发者的说明填写。
LETTERBOX_CHANNEL要打开的频道名称。通常由 letterbox PTY 父进程在启动此服务器时设置;仅在单独运行 MCP 服务器时才手动设置。查看英文原文
Channel name to open. Normally set by the letterbox PTY-parent when it spawns this server; set it manually only when running the MCP server standalone.LETTERBOX_SENDER此端点在通道上的身份,即对端代理在每条消息中看到的名称。查看英文原文
This endpoint's identity on the channel — the name the peer agent sees on every message.LETTERBOX_INSTANCE_ID每次启动的实例 ID,是 watcher/自写入的关联键,防止代理把自己的消息当作收到的消息。每次启动必须唯一。查看英文原文
Per-launch instance id, the watcher/own-write join key that stops an agent seeing its own messages as incoming. Must be unique per launch.
说明为自动翻译,变量名保持原样;不确定时请查看原文。
填写你的密钥
在 Letterbox 的设置中,LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID 还是空的,填入你的密钥并保存
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 Letterbox 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Letterbox,或回答中出现 Letterbox 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要填写 3 项设置(LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID) · 需要先在电脑上安装 Python (uv)(只需一次)
让 AI 帮你安装
把这段话复制到 VS Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 VS Code 安装 MCP server Letterbox,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "letterbox": { "type": "stdio", "command": "uvx", "args": [ "letterbox" ], "env": { "LETTERBOX_CHANNEL": "your-value", "LETTERBOX_SENDER": "your-value", "LETTERBOX_INSTANCE_ID": "your-value" } } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID 先保留 "your-value",请我自己把真实值粘贴到文件或应用的输入框里。不要让我在对话里输入密钥。5) 按约定执行,然后确认 Letterbox 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 uv(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --version- 显示版本号(例如 uv …)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
uv --version安装一次,所有需要 uv 的工具都能用
填写 3 项设置
这些是程序设置,不是密钥,无需注册。按开发者的说明填写。
LETTERBOX_CHANNEL要打开的频道名称。通常由 letterbox PTY 父进程在启动此服务器时设置;仅在单独运行 MCP 服务器时才手动设置。查看英文原文
Channel name to open. Normally set by the letterbox PTY-parent when it spawns this server; set it manually only when running the MCP server standalone.LETTERBOX_SENDER此端点在通道上的身份,即对端代理在每条消息中看到的名称。查看英文原文
This endpoint's identity on the channel — the name the peer agent sees on every message.LETTERBOX_INSTANCE_ID每次启动的实例 ID,是 watcher/自写入的关联键,防止代理把自己的消息当作收到的消息。每次启动必须唯一。查看英文原文
Per-launch instance id, the watcher/own-write join key that stops an agent seeing its own messages as incoming. Must be unique per launch.
说明为自动翻译,变量名保持原样;不确定时请查看原文。
填写你的密钥
在 Letterbox 的设置中,LETTERBOX_CHANNEL, LETTERBOX_SENDER, LETTERBOX_INSTANCE_ID 还是空的,填入你的密钥并保存
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 Letterbox 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Letterbox,或回答中出现 Letterbox 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
开发者专用:终端命令和 JSON 设置
安装在电脑上
Claude Code
claude mcp add --scope user letterbox --env LETTERBOX_CHANNEL=your-value --env LETTERBOX_SENDER=your-value --env LETTERBOX_INSTANCE_ID=your-value -- uvx letterboxClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"letterbox": {
"command": "uvx",
"args": [
"letterbox"
],
"env": {
"LETTERBOX_CHANNEL": "your-value",
"LETTERBOX_SENDER": "your-value",
"LETTERBOX_INSTANCE_ID": "your-value"
}
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"letterbox": {
"command": "uvx",
"args": [
"letterbox"
],
"env": {
"LETTERBOX_CHANNEL": "your-value",
"LETTERBOX_SENDER": "your-value",
"LETTERBOX_INSTANCE_ID": "your-value"
}
}
}
}VS Code (mcp.json)
{
"servers": {
"letterbox": {
"type": "stdio",
"command": "uvx",
"args": [
"letterbox"
],
"env": {
"LETTERBOX_CHANNEL": "your-value",
"LETTERBOX_SENDER": "your-value",
"LETTERBOX_INSTANCE_ID": "your-value"
}
}
}
}需要你填写的值
LETTERBOX_CHANNEL必填 env要打开的频道名称。通常由 letterbox PTY 父进程在启动此服务器时设置;仅在单独运行 MCP 服务器时才手动设置。查看英文原文
Channel name to open. Normally set by the letterbox PTY-parent when it spawns this server; set it manually only when running the MCP server standalone.LETTERBOX_SENDER必填 env此端点在通道上的身份,即对端代理在每条消息中看到的名称。查看英文原文
This endpoint's identity on the channel — the name the peer agent sees on every message.LETTERBOX_INSTANCE_ID必填 env每次启动的实例 ID,是 watcher/自写入的关联键,防止代理把自己的消息当作收到的消息。每次启动必须唯一。查看英文原文
Per-launch instance id, the watcher/own-write join key that stops an agent seeing its own messages as incoming. Must be unique per launch.
说明为自动翻译,变量名保持原样;不确定时请查看原文。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它能做什么
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月19日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 dovahkiin-v 验证,该账户拥有此仓库
- ✓ 通过
仍在维护
代码最后更新于3个月前
- ✓ 通过
有许可证
使用 MIT
- – 不适用
端点有响应
它在你的电脑上运行,没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行,改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行;我们只能读取互联网端点的工具列表
已公开的漏洞(OSV.dev)
OSV.dev 中没有 letterbox@1.2.2 的记录
只检查这个版本的包本身,不包括所有依赖 · 检查于 2026年11月16日
作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/dovahkiin-v-letterbox)讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“开发者工具”中的其他服务器比较i
- 星标数多于此分类中其他 6116 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 6116 个服务器的 28% 更新
- 基础检查结果等于或优于此分类中其他 6116 个服务器的 99%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Letterbox 安全吗?
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
它还在维护吗?
GitHub 仓库最后更新于3个月前,最新版本(1.2.2)于3个月前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
有什么可以替代它?
同一分类中有:GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
功能相近的其他选择
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
GitDiagram
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Appllama
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Omnara
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Repowise
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
| 本项 Letterbox | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 云端或安装在电脑上都可以 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 是 | 否 | 否 |
| 基础检查 | 3/3 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| 许可证 | MIT | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Letterbox
📌 Built for internal production use. Architecture proven across months of daily AI development. Open-sourced as a reference implementation. I use it almost daily.
If you use AI coding assistants in the terminal, you normally work with one at a time — and getting two of them to collaborate means copy-pasting messages between windows yourself. Letterbox lets two assistants (say, Claude and Gemini, or Gemini and Mistral's Vibe) talk *directly* to each other and work a task together, hands-free.
The result: one agent can plan while another reviews, or the two can split the work between them — collaborating on their own while you watch, instead of relaying every message by hand.
*A small file-based comms protocol that lets two AI agents in separate terminals talk to each other in real time.*
Letterbox lets two terminal coding agents — Claude Code, Gemini CLI, Antigravity, or Mistral's Vibe — hold a real-time conversation by passing message files through a shared directory. When one agent speaks, a 📬 notification is injected into the other's terminal and wakes it to read and reply. No network, no server, no shared memory: just JSON files in a folder and the OS's atomic-rename. It's the messaging layer that was built for an internal planning loop, extracted into a standalone, versioned tool in 2026. If you've ever wanted two CLI agents to collaborate on a task without you copy-pasting between windows, this is for you. It gets the occasional update at the author's whim (the launcher tells you when a newer one is out) — but it's currently unsupported small project, not a community one.
The bridge is cross-harness: Claude on one side, Gemini on the other, talking through the same channel, has been verified live. The one wrinkle is setup — Claude wires itself automatically, while Gemini and Antigravity load letterbox from their own settings. The Setup section walks through both.
Why it exists
I work with two AI collaborators every day — Claude and Gemini — each living in whatever terminal harness it runs in (Claude Code, Gemini CLI, Antigravity CLI, and now Mistral's Vibe). Letterbox is how I get them talking to *each other* instead of through me.
That happens in two modes. Sometimes it's manual: we're brainstorming and I want to loop the other model into the conversation. Sometimes it's automated — in the planning loop, Claude drafts a plan and each plan is routed to Gemini for review as a built-in stage. Letterbox carries both the same way.
It's harness-agnostic by design — Claude Code ↔ Gemini CLI ↔ Antigravity CLI ↔ Vibe in any combination — and same-model pairs work just as well: two Claude tabs, or two Gemini tabs, talking over one channel.
What it is
Each letterbox launch runs two coordinated processes inside one terminal:
letterbox claude --channel demo --as alice
│ ├─ PTY-Parent (the foreground letterbox process) │ • spawns the harness CLI as a PTY child │ • watches the channel directory for peer writes │ • injects 📬 notifications into the PTY on arrival │ └─ the harness spawns: └─ letterbox mcp (stdio MCP server, agent-spawned) • send_message / check_messages / acknowledge • check_latest_message / channel_info / list_channels
Both sides coordinate ONLY through the filesystem:
~/.letterbox/channels/demo/ msg-*.json ← one file per message .read/alice.json ← per-agent read markers .read/bob.json
There is no daemon, no IPC, no background service. The filesystem *is* the coordination medium — the PTY-Parent's watcher sees a new msg-*.json appear and renders a notification; the channel directory is durable, inspectable, and cat-able. Crash recovery is trivial because nothing valuable lives in memory.
How the agent gets the letterbox tools differs per harness, and it's the one thing you configure once:
- Claude Code takes a launch flag, so letterbox wires it *automatically* — it generates a temporary MCP config and passes
--mcp-configtoclaude. Nothing for you to set up. - Gemini CLI and Antigravity don't take that flag; they load MCP servers from their own settings file. You add a one-line, channel-agnostic
letterboxentry there once, and the launcher hands each session its channel and identity through environment variables at launch — so you never edit settings per channel. - Vibe loads MCP servers from
~/.vibe/config.toml. Its MCP subprocess inherits only a trimmed environment, so a one-time bridge script is needed to relayLETTERBOX_CHANNEL/LETTERBOX_SENDERfrom Vibe's own process env. Once that's in place, any channel works exactly like Gemini. See the Vibe setup section.
Who it's for
- People running terminal coding agents who want autonomous AI↔AI dialogue on one machine, without babysitting copy-paste between windows.
- People who value files as the source of truth — auditable, greppable, no opaque protocol, no magic.
Who it's NOT for
- Anyone wanting a hosted or networked chat service — the message protocol is filesystem-local and never touches the network. (The launcher makes one optional, best-effort version check at startup; disable it with
LETTERBOX_NO_UPDATE_CHECK=1.) - Anyone wanting a multi-user platform — it's a point-to-point bridge between agents on one machine, not a many-user hub (see Built for two).
- Windows-native users — v1 is POSIX-only (see What we don't support).
- Anyone wanting a supported product — letterbox is versioned and gets the occasional update at the author's whim (the launcher tells you when a newer one is out), but there's no roadmap, no SLA, and no commitment to take feature requests or keep maintaining it. Use it as-is; pull a newer version if it helps.
Built for two
Letterbox is a two-way bridge at heart — one peer talking to one peer is what it's designed and tuned for. Three or more agents *can* share a channel: directed addressing (send_message(to=" ")) and the participants list make it workable, and same-channel broadcasts reach everyone. But a shared channel is a broadcast bus — every message wakes every participant. Without orchestration (turn-taking, a designated coordinator, or rules about who speaks when), an N-way room becomes a notification storm that can chew through a model's message/usage limits surprisingly fast. If you want three or more, bring your own conductor. The substrate is honest about who's in the room; the etiquette is on you.
Install
Available on PyPI and the MCP Registry.
pip install letterbox
Or from source:
pip install -e . # or: pip install -e ".[dev]" for the test extras
This puts the letterbox command on your PATH. The command must resolve by name — each agent spawns letterbox mcp itself — so this is load-bearing. Confirm it:
which letterbox # note this absolute path; Gemini/Antigravity setup needs it
You also need the harness you're launching (claude, gemini, antigravity, or vibe) installed, on your PATH, and logged in. Letterbox launches it for you.
Updating
Letterbox is versioned (letterbox.__version__, the single source of truth) and published to PyPI. On a human-facing launch the CLI makes one best-effort check (at most once a day, cached under ~/.cache/letterbox/) and prints a one-line notice if a newer version exists. To update:
pip install --upgrade letterbox
This is the only network call letterbox ever makes — the messaging protocol stays fully local. It runs with a tight timeout and is fully fail-silent: if it can't reach GitHub it simply prints nothing and never delays your launch. It is never run for letterbox mcp (the agent's stdio server). Disable it entirely with LETTERBOX_NO_UPDATE_CHECK=1.
Setup per harness
You only do this once per harness. Skip the harnesses you won't use.
Claude Code — nothing to do
Letterbox wires Claude automatically: at launch it writes a temporary MCP config (mode 0600) and passes --mcp-config to claude. The letterbox tools appear in that session and nowhere else. There is no settings file to edit.
Gemini CLI — two one-time steps
1. Register the MCP server in ~/.gemini/settings.json (create the file if it doesn't exist). Use the absolute path to your installed letterbox (from which letterbox above), and pass only ["mcp"] — no channel, no identity:
{
"mcpServers": { "letterbox": { "command": "/absolute/path/to/letterbox", "args": ["mcp"] } } }
This entry is channel-agnostic on purpose. The launcher exports LETTERBOX_CHANNEL, LETTERBOX_SENDER, and LETTERBOX_INSTANCE_ID into Gemini's environment at launch, and the MCP server reads them — so the same single entry serves every channel and you never edit it again. (This mirrors how the Forge orchestrators pass a channel via an env var.)
2. Trust the folder you launch from. Gemini refuses to run in an untrusted directory without an interactive *"do you trust this folder?"* prompt — and a blocking TUI prompt would stall the automation. Pre-trust the launch directory (or a parent) in ~/.gemini/trustedFolders.json:
{
"/home/you/projects": "TRUST_PARENT" }
TRUST_FOLDER trusts exactly that directory; TRUST_PARENT trusts it and everything beneath, so one entry covers all your project folders. (Tip: don't reach for Gemini's --skip-trust flag to dodge this — it forces a workspace-system-prompt lookup that crashes even in already-trusted directories. Trust the folder instead.)
Antigravity (agy)
Launch it as `letterbox agy …` (the long form letterbox antigravity … also works — agy is just an alias matching the binary name). Antigravity receives its per-launch channel and identity through the same environment variables as Gemini; what differs is how you register the MCP server. agy loads MCP servers from plugins, so you install letterbox as a tiny local plugin (a directory with two JSON files):
# 1. Build the plugin (one directory, two files). Use the absolute
letterbox path from which letterbox.
mkdir -p ~/.letterbox/agy-plugin/letterbox cat > ~/.letterbox/agy-plugin/letterbox/plugin.json <<'JSON' { "name": "letterbox", "version": "1.0.0", "description": "Letterbox file-based AI-to-AI comms bridge." } JSON cat > ~/.letterbox/agy-plugin/letterbox/mcp_config.json <<'JSON' { "mcpServers": { "letterbox": { "command": "/absolute/path/to/letterbox", "args": ["mcp"] } } } JSON
2. Install it (and confirm).
agy plugin install ~/.letterbox/agy-plugin/letterbox agy plugin list
The mcp_config.json is channel-agnostic for the same reason Gemini's settings entry is — the launcher passes the channel and identity by environment at launch. Like Gemini, agy