mirror of https://github.com/dtzp555-max/ocp.git synced 2026-07-21 21:15:09 +00:00

Files

T

taodengandClaude Opus 4.6 593d0dcd5f Initial release: OpenAI-compatible proxy for Claude CLI

Routes OpenClaw requests through `claude -p` CLI, letting you use
Claude Pro/Max subscriptions as a model provider without API keys.

- SSE streaming + non-streaming responses
- Auto-setup script for OpenClaw configuration
- Supports Opus 4.6, Sonnet 4.6, Haiku 4

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-16 21:47:12 +10:00

3.5 KiB

Raw Permalink Blame History

openclaw-claude-proxy

Use your Claude Pro/Max subscription as an OpenClaw model provider — no API key needed.

How it works

OpenClaw Gateway → proxy (localhost:3456) → claude -p CLI → Anthropic (via OAuth)

The proxy translates OpenAI-compatible /v1/chat/completions requests into claude -p CLI calls. Anthropic sees normal Claude Code usage under your subscription — no API billing, no separate key.

Prerequisites

Node.js ≥ 18
Claude CLI installed and authenticated (claude login)
OpenClaw installed

Quick Install

# Clone
git clone https://github.com/dtzp555-max/openclaw-claude-proxy.git
cd openclaw-claude-proxy

# Auto-configure OpenClaw + start proxy
node setup.mjs

That's it. The setup script will:

Verify Claude CLI is installed and authenticated
Add claude-local provider to openclaw.json
Add auth profiles to all agents
Start the proxy

Then set your preferred Claude model as default:

openclaw config set agents.defaults.model.primary "claude-local/claude-opus-4-6"
openclaw gateway restart

Manual Install

1. Start the proxy

node server.mjs
# or in background:
bash start.sh

2. Configure OpenClaw

Add to ~/.openclaw/openclaw.json under models.providers:

"claude-local": {
  "baseUrl": "http://127.0.0.1:3456/v1",
  "api": "openai-completions",
  "authHeader": false,
  "models": [
    {
      "id": "claude-opus-4-6",
      "name": "Claude Opus 4.6",
      "reasoning": true,
      "input": ["text"],
      "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
      "contextWindow": 200000,
      "maxTokens": 16384
    },
    {
      "id": "claude-sonnet-4-6",
      "name": "Claude Sonnet 4.6",
      "reasoning": true,
      "input": ["text"],
      "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
      "contextWindow": 200000,
      "maxTokens": 16384
    },
    {
      "id": "claude-haiku-4",
      "name": "Claude Haiku 4",
      "reasoning": false,
      "input": ["text"],
      "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
      "contextWindow": 200000,
      "maxTokens": 8192
    }
  ]
}

3. Set as default model

openclaw config set agents.defaults.model.primary "claude-local/claude-opus-4-6"
openclaw gateway restart

Available Models

Model ID	Claude CLI model	Notes
`claude-opus-4-6`	opus	Most capable, slower
`claude-sonnet-4-6`	sonnet	Good balance of speed/quality
`claude-haiku-4`	haiku	Fastest, lightweight

Environment Variables

Variable	Default	Description
`CLAUDE_PROXY_PORT`	`3456`	Listen port
`CLAUDE_BIN`	`claude`	Path to claude binary
`CLAUDE_TIMEOUT`	`120000`	Request timeout (ms)

API Endpoints

GET /v1/models — List available models
POST /v1/chat/completions — Chat completion (streaming + non-streaming)
GET /health — Health check

Add to your ~/.zshrc:

bash ~/.openclaw/projects/claude-proxy/start.sh 2>/dev/null

Notes

Cost shows as $0 because billing goes through your Claude subscription
The 🔑 field in /status may show the dummy auth key — this is normal
Each request spawns a claude -p process; concurrent requests are supported
The proxy must run on the same machine as the Claude CLI (uses local OAuth)

License

MIT

3.5 KiB Raw Permalink Blame History