mirror of
https://github.com/tiennm99/claude-central-gateway.git
synced 2026-04-17 15:20:33 +00:00
tiennm99
bfb936ae4a
- Add main proxy endpoint (api/v1/messages.js) - Add token validation via GATEWAY_TOKEN - Add model mapping via MODEL_MAP env var - Support full SSE streaming in Anthropic format - Add package.json with openai dependency - Add vercel.json for routing config - Update README with Quick Start guide - Consolidate memory to .claude/memory/ Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
72 lines
2.3 KiB
Markdown
72 lines
2.3 KiB
Markdown
# Claude Central Gateway
|
|
|
|
A proxy for Claude Code that routes requests to your preferred third-party API provider. Easily hosted on Vercel, Netlify, and similar platforms.
|
|
|
|
## Where to Find Cheap LLM Providers?
|
|
|
|
Check out [this repo](https://github.com/tiennm99/penny-pincher-provider) for a list of affordable LLM providers compatible with this gateway.
|
|
|
|
## Philosophy
|
|
|
|
Minimal, simple, deploy anywhere.
|
|
|
|
## Quick Start
|
|
|
|
### 1. Deploy to Vercel
|
|
|
|
[](https://vercel.com/new/clone?repository-url=https://github.com/tiennm99/claude-central-gateway)
|
|
|
|
Or manually:
|
|
|
|
```bash
|
|
git clone https://github.com/tiennm99/claude-central-gateway
|
|
cd claude-central-gateway
|
|
vercel
|
|
```
|
|
|
|
### 2. Set Environment Variables
|
|
|
|
In Vercel dashboard, set these environment variables:
|
|
|
|
| Variable | Description | Example |
|
|
|----------|-------------|---------|
|
|
| `GATEWAY_TOKEN` | Shared token for authentication | `my-secret-token` |
|
|
| `OPENAI_API_KEY` | Your OpenAI API key | `sk-...` |
|
|
| `MODEL_MAP` | Model name mapping | `claude-sonnet-4-20250514:gpt-4o` |
|
|
|
|
### 3. Configure Claude Code
|
|
|
|
```bash
|
|
export ANTHROPIC_BASE_URL=https://your-gateway.vercel.app
|
|
export ANTHROPIC_AUTH_TOKEN=my-secret-token
|
|
claude
|
|
```
|
|
|
|
## Environment Variables
|
|
|
|
| Variable | Required | Description |
|
|
|----------|----------|-------------|
|
|
| `GATEWAY_TOKEN` | Yes | Token users must provide in `ANTHROPIC_AUTH_TOKEN` |
|
|
| `OPENAI_API_KEY` | Yes | OpenAI API key |
|
|
| `MODEL_MAP` | No | Comma-separated model mappings (format: `claude:openai`) |
|
|
|
|
## Why This Project?
|
|
|
|
### Why not use a local proxy, like [Claude Code Router](https://github.com/musistudio/claude-code-router)?
|
|
|
|
Local proxies only work on a single machine. This project serves multiple machines simultaneously.
|
|
|
|
### Why not use [LiteLLM](https://github.com/BerriAI/litellm)?
|
|
|
|
LiteLLM requires a dedicated VPS, consumes more resources, and costs more to deploy.
|
|
|
|
### Why no advanced features like routing or GUI management?
|
|
|
|
Built for personal use. Simplicity over features.
|
|
|
|
## Not Suitable For
|
|
|
|
- **Single-machine localhost proxy** → Highly recommend [Claude Code Router](https://github.com/musistudio/claude-code-router)
|
|
- **Enterprise/Team usage with GUI management** → Use [LiteLLM](https://github.com/BerriAI/litellm)
|
|
- **Advanced routing, load balancing, rate limiting** → Use [LiteLLM](https://github.com/BerriAI/litellm) or similar
|