AI Skill Hub 强烈推荐:claude_codex_bridge Agent工作流 是一款优质的Agent工作流。已获得 2.7k 颗 GitHub Star,AI 综合评分 8.2 分,在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案,这是一个值得深入了解的选择。
支持Claude、Codex、Gemini等多个AI模型的开源工作流框架。提供可视化多智能体协作CLI环境,适合需要多模型协同完成复杂任务的开发者和AI应用构建者。
claude_codex_bridge Agent工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
支持Claude、Codex、Gemini等多个AI模型的开源工作流框架。提供可视化多智能体协作CLI环境,适合需要多模型协同完成复杂任务的开发者和AI应用构建者。
claude_codex_bridge Agent工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install claude_codex_bridge
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install claude_codex_bridge
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/SeemSeam/claude_codex_bridge
cd claude_codex_bridge
pip install -e .
# 验证安装
python -c "import claude_codex_bridge; print('安装成功')"
# 命令行使用
claude_codex_bridge --help
# 基本用法
claude_codex_bridge input_file -o output_file
# Python 代码中调用
import claude_codex_bridge
# 示例
result = claude_codex_bridge.process("input")
print(result)
# claude_codex_bridge 配置文件示例(config.yml) app: name: "claude_codex_bridge" debug: false log_level: "INFO" # 运行时指定配置文件 claude_codex_bridge --config config.yml # 或通过环境变量配置 export CLAUDE_CODEX_BRIDGE_API_KEY="your-key" export CLAUDE_CODEX_BRIDGE_OUTPUT_DIR="./output"
Install or update an npm-managed CCB with npm:
npm install -g @seemseam/ccb@latest
For GitHub release-package or source installs, use CCB's transactional updater:
ccb update
On an npm-managed install, ccb update prints the equivalent npm command and does not modify npm's vendored payload in place.
<details> <summary><b>Native Windows x64 beta</b></summary>
The Windows beta artifact is attached to the matching stable CCB GitHub release. Download ccb-windows-x86_64.zip and its .sha256 sidecar, verify the digest, extract the ZIP, then run:
.\install.ps1 install -Yes
ccb --print-version
It requires native Windows x64, Python 3.10+, WezTerm, Git Bash, and Herdr 0.8.0 or newer. The installer creates an install-local managed Python runtime. The binaries are unsigned, and ccb update remains diagnostic-only for this beta support tier; install a later Windows build by rerunning its validated install.ps1.
</details>
CCB-managed provider panes suppress known provider-native startup update prompts. After updating CCB—or immediately when CCB is already current—ccb update checks installed provider CLIs and offers supported updates once. Use --providers check, --providers all, or --providers none for explicit report-only, non-interactive update, or skip behavior. Declining prompts again on the next ccb update; skipping a version hides only that exact version. CCB never restarts active provider panes during this flow, so an accepted provider update applies when that pane next starts or is explicitly restarted.
After a release change, the newly installed CCB also retires old project-scoped Claude/Gemini caches. Manifest-valid caches for deleted projects are removed immediately. A stopped current project is cleaned immediately; active or other existing projects are preserved and cleaned after their next successful ccb kill. Unknown providers, malformed manifests, foreign symlinks, sessions/auth, and the user-scoped Gemini cache are never removed by this migration. Use ccb update --no-cache-cleanup to skip it for one update.
To roll back, use the same transactional updater with an older released version, for example ccb update 8.1.3. CCB rejects a same-version artifact whose build identity differs from the installed build, and restores the prior local prefix if the update transaction fails. If restoration itself cannot complete, CCB retains and reports the external recovery backup path.
<details> <summary><b>GitHub release package and source install fallbacks</b></summary>
If npm is not convenient in your environment, download the matching package from Releases, unpack it, and install:
tar -xzf ccb-*.tar.gz
cd ccb-*
./install.sh install
Source install is intended only for development or temporary fallback:
git clone https://github.com/SeemSeam/claude_codex_bridge.git
cd claude_codex_bridge
./install.sh install
Source install links global ccb / ask back to the checkout. Regular users should prefer the npm package.
</details>
<a id="quick-start"></a>
A blank project starts light: CCB opens one main window with a single agent named demo, selecting the first supported CLI available on the machine (Codex, Claude, Gemini, then other providers). It no longer mounts a multi-agent team by default.
Click the ⚙ Settings icon at the top-left of the CCB sidebar to open the local configuration control panel. You can also run ccb config ui from the project directory.
The Config UI always binds to loopback. To use a stable local port and token, configure a token source in .ccb/ccb.config; never put a literal token in that file:
```toml [config_ui] port = 43123 token_env = "CCB_CONFIG_UI_TOKEN"
`--port` remains a one-run override. `token_file` must be project-relative, non-symlinked, and owner-only (`chmod 600 .ccb/config-ui.token` on POSIX). Without a token source, CCB keeps the existing random token and ephemeral-port behavior. The CLI prints only the loopback URL and token source, never the token value.
<p align="center">
<img src="assets/readme_v7/config-control-panel.png" alt="CCB configuration control panel editing the default demo agent" width="960">
</p>
The panel edits windows, pane splits, providers, models, thinking levels, API overrides, workspaces, Rich mode, and sidebar settings. It validates changes before saving and supports reload dry-runs and guarded hot reload. Saving creates `.ccb/ccb.config` and pins the selected provider and topology for this project.
For an advanced multi-agent topology, edit it visually or create `.ccb/ccb.config` manually. In v2 `[windows]`, `,` and `;` control vertical stacking and horizontal splits inside each window, so `A,B;C,D` is close to a four-pane layout.
toml version = 2
[windows] main = "main:codex" work = "worker1:codex(worktree), worker2:claude(worktree)" review = "reviewer:claude, qa:gemini"
[ui.sidebar] mode = "every_window" width = "15%" bottom_height = 20 agents_height = "50%" comms_height = "15%" tips_height = "35%" comms_limit = 3
Validate the config and start the workspace:
bash ccb config validate ccb ```
claude_codex_bridge (CCB) 是一个专为 Agent 设计的桥接工具,旨在通过统一的接口实现不同 AI Agent 之间的协作与通信。它不仅能让开发者在终端中高效调度多个 Agent,还能通过灵活的指令机制,让 Agent 之间实现自主的任务委派与协同工作,构建高效的 AI 协作工作流。
最新版本已实现重大更新:macOS 侧边栏现已支持原生 Universal Binary,完美兼容 Intel 与 Apple Silicon 芯片;同时,Release CI 流程已集成自动化验证,确保 macOS 辅助工具在上传前通过 smoke-test 校验。此外,Linux 侧边栏功能也得到了持续优化,提升了跨平台的交互体验。
在使用本项目之前,请确保您的开发环境已安装 Python 3.10 或更高版本。此外,由于项目涉及终端交互与会话管理,建议在 Unix-like 环境下配合 tmux 使用,以获得最佳的终端操作体验。
本项目支持多种环境的安装。对于 Unix-like 系统(包括 Linux、macOS 及 WSL),请克隆仓库后运行 `./install.sh install` 进行安装;若在 Windows 原生环境下运行 Agent CLI,请使用 PowerShell 进行相关配置。如需移除或重新安装,可直接使用 `ccb uninstall` 或 `ccb reinstall` 命令。
CCB 采用“Agent 优先”的设计理念。用户可以通过显式指令(如使用 `/ask` 或 `$ask` 前缀)来指定特定的 Agent 执行任务,例如 `/ask reviewer review the changes`。同时,CCB 也支持隐式委派模式,允许 Agent 根据上下文自主决定是否调用其他 Agent 来完成复杂任务。
CCB 的配置遵循严格的分层优先级机制:项目级配置 `.ccb/ccb.config` 优先级最高,其次是用户级配置 `~/.ccb/ccb.config`,最后是内置默认配置。这种设计确保了项目特定的行为不会污染全局环境。此外,项目还支持通过 `.ccb/ccb_memory.md` 实现项目范围内的共享记忆机制。
CCB 作为 Agent CLI Hub,致力于实现“每一次交互皆可见”与“每一个模型皆可控”的核心理念。它为开发者提供了一套强大的接口能力,支持在团队协作中灵活调度不同的 AI 模型,确保在复杂的 Agent 协作流中,开发者能够精准掌控每一个交互环节与模型输出。
CCB 深度集成了现代编辑器(如 Neovim),实现了代码编写与 AI 评审的无缝衔接。开发者可以在 Neovim 中进行代码编写,而后台的 Agents 则可以并行地进行代码审查、迭代与测试,构建起一套“编写-评审-迭代”自动化循环的高效开发工作流。
架构设计完善,支持多模型协作是核心优势。社区活跃度高(2.7k星),文档充分,适合企业级AI应用构建。
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
总体来看,claude_codex_bridge Agent工作流 是一款质量优秀的Agent工作流,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | claude_codex_bridge |
| 原始描述 | 开源AI工作流:Visible multi-agent CLI teams for Claude, Codex, Gemini, OpenCode, and Droid wit。⭐2.7k · Python |
| Topics | 多智能体工作流CLI工具AI协作跨模型 |
| GitHub | https://github.com/SeemSeam/claude_codex_bridge |
| License | NOASSERTION |
| 语言 | Python |
收录时间:2026-05-17 · 更新时间:2026-05-19 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端