# CLIProxyAPI — Local Proxy for AI Coding CLIs

> CLIProxyAPI runs a local proxy that exposes OpenAI/Gemini/Claude/Codex-compatible endpoints for CLI tools. Configure YAML, then start with docker compose.

## Install

Save as a script file and run:

## Quick Use

1. Install the verified entrypoint:

```bash
git clone https://github.com/router-for-me/CLIProxyAPI && cd CLIProxyAPI && cp config.example.yaml config.yaml
```

2. Run a first local check:

```bash
docker compose up -d --build
```

3. Add a repeatable verification step:

```bash
curl -s http://127.0.0.1:8317/v1/models | head
```

---

## Intro

CLIProxyAPI is a verified GitHub-backed asset sourced from `router-for-me/CLIProxyAPI` with 32,053 stars and a MIT license snapshot. Best for: power users who want one local API surface to route multiple CLI-backed accounts/providers into SDKs and tools. Works with: Docker + docker compose; exposes OpenAI/Gemini/Claude/Codex-compatible endpoints (per repo). Setup time: 15 minutes.

### Quantitative notes

- Default service port 8317 (repo config)
- Docker compose exposes multiple ports (repo docker-compose.yml)

---

## Deep Dive

### What it solves

Use this when you need a **repeatable, team-shareable workflow** instead of one-off agent prompts. The goal is to make installation, first-run validation, and rollback **predictable**.

### Minimal mental model

- Treat the GitHub repo as the source of truth: install instructions, configs, and upgrade paths live there.
- Keep your first run small: one command, one verification, one rollback plan.
- Capture a baseline: setup time, first successful run, and one real task completed end-to-end.

### Safe rollout checklist

1. **Verify source**: confirm repo URL, stars, and license match what you expect.
2. **Install** using the Quick Use commands above.
3. **Prove it works** with the verification command; save the output in a note or issue.
4. **Operationalize**: document owner, upgrade command, and rollback command.

### Troubleshooting (common)

- **Install succeeds but nothing shows up**
  - Likely cause: the tool needs a restart/reload (CLI/IDE) or a config file in the right path.
  - Fix: restart the client, then re-run the verification step.

- **Works on one machine, fails on another**
  - Likely cause: Node/Python/Docker versions differ or missing system dependencies.
  - Fix: pin versions (Node/Python), and copy a minimal known-good config.

- **Token cost or latency is worse than expected**
  - Likely cause: tool schemas or verbose outputs get injected into context.
  - Fix: prefer smaller steps, cache results, and keep tool responses concise when possible.


---

### FAQ

**Q: Is it safe to expose publicly?**
A: The repo config supports binding host; keep it on localhost unless you fully understand auth keys and firewalling.

**Q: How do I add credentials?**
A: Use the repo's YAML config (api-keys + provider sections) and keep secrets outside git.

**Q: How do I debug routing issues?**
A: Check container logs, then validate `/v1/models` and one minimal request before integrating a full client.

---

## Source & Thanks

> GitHub: https://github.com/router-for-me/CLIProxyAPI
> Owner avatar: https://avatars.githubusercontent.com/u/233033915?v=4
> License (SPDX): MIT
> Stars (verified via `api.github.com/repos/router-for-me/CLIProxyAPI`): 32,053


---

<!-- ZH -->

# CLIProxyAPI——AI 编程 CLI 的本地代理

> CLIProxyAPI 在本地启动代理服务，为 CLI 工具提供 OpenAI/Gemini/Claude/Codex 兼容接口与路由。按示例创建 config.yaml，并用 docker compose 启动容器，即可在 8317 等端口提供服务。

## 快速使用

1. 安装（以仓库为准）：

```bash
git clone https://github.com/router-for-me/CLIProxyAPI && cd CLIProxyAPI && cp config.example.yaml config.yaml
```

2. 首次运行/检查：

```bash
docker compose up -d --build
```

3. 可重复验证：

```bash
curl -s http://127.0.0.1:8317/v1/models | head
```

---

## 简介

CLIProxyAPI 已核验来源于 `router-for-me/CLIProxyAPI`（32,053 stars，许可证 MIT）。适合：想把多账号/多 provider 的 CLI 能力统一成一个本地 API 面的重度用户与团队。兼容：Docker + docker compose；对外暴露 OpenAI/Gemini/Claude/Codex 兼容接口（见仓库说明）。装机时间：15 分钟。

### 量化信息

- 默认端口 8317（仓库配置）
- docker-compose.yml 暴露多个端口（仓库）

---

## 深度说明

### 解决什么问题

把“找到项目 → 安装 → 首次验证 → 回滚/升级”变成可复用流程，避免只靠一次性提示词或截图操作。

### 最小心智模型

- GitHub 仓库是事实来源：安装、配置、升级、已知问题都以它为准。
- 第一次只做最小闭环：一个命令安装、一个命令验证、一个可回滚方案。
- 记录基线：装机耗时、首次成功输出、完成 1 个真实任务的证据。

### 安全推广清单

1. **核验来源**：确认仓库 URL / stars / license 与预期一致。
2. 按“快速使用”完成安装与首次检查。
3. 跑通“验证命令”，把输出留档。
4. 标注 owner，并写清升级/回滚步骤。

### 常见排障

- **装了但看不到效果**
  - 常见原因：需要重启 CLI/IDE 或配置文件路径不对。
  - 处理：重启后再跑一遍“验证命令”。

- **一台机器能跑，另一台不行**
  - 常见原因：Node/Python/Docker 版本差异或缺少系统依赖。
  - 处理：固定版本，并拷贝最小可用配置。

- **token 成本/延迟超预期**
  - 常见原因：工具 schema 或输出过长被塞进上下文。
  - 处理：拆小步骤、缓存结果、尽量让工具输出更短。


---

### FAQ

**Q: 能直接公网暴露吗？**
A: 配置支持绑定 host；除非你完全理解认证与网络边界，否则只建议跑在 localhost。

**Q: 怎么添加凭据？**
A: 按仓库 YAML 配置填 api-keys 与各 provider 段，密钥不要提交到 git。

**Q: 路由不对怎么排查？**
A: 先看容器日志，再用 `/v1/models` 做最小验证，最后再接入完整客户端/SDK。

---

## 来源与感谢

> GitHub：https://github.com/router-for-me/CLIProxyAPI
> Owner avatar：https://avatars.githubusercontent.com/u/233033915?v=4
> 许可证（SPDX）：MIT
> GitHub stars（已通过 `api.github.com/repos/router-for-me/CLIProxyAPI` 核验）：32,053


---
Source: https://tokrepo.com/en/workflows/cliproxyapi-local-proxy-for-ai-coding-clis
Author: Script Depot