Implements issue #12 section 14 Path A. Lets OCP admin designate a single well-known "anonymous" key that bypasses validateKey() while keeping AUTH_MODE=multi. Gives OpenClaw multi-agent clients (which MUST send a non-empty Authorization header per their per-agent auth-profiles schema) a way to connect without every user needing a personal key. ## Background After PR-1 (issue #12), we know OpenClaw multi-agent setups require a per-agent auth-profiles.json with a non-empty `key` field. OCP multi-mode rejects any non-empty Bearer token that isn't in the keys database (server.mjs line 1152), which creates a deadlock: the only way for OpenClaw to use OCP is with a real admin-issued key. Path A resolves this by letting the admin opt in to a public anonymous key that clients can auto-discover via /health. OpenClaw writes this key into its agent profiles just like a real key; OCP server short-circuits validateKey when the key matches the allowlist. No per-user coordination needed, admin still controls the policy (can rotate, can unset, can rate-limit). ## Changes ### server.mjs * Line 100-103: new `PROXY_ANONYMOUS_KEY` env var + warning if set while AUTH_MODE is not multi. * Line 1127-1138 (localhost branch): anonymous allowlist short-circuit before validateKey so localhost clients using the anon key are labeled "anonymous" instead of "local" in stats. * Line 1153-1163 (multi branch): the same allowlist check between the ADMIN_KEY check and validateKey. Uses timingSafeEqual with explicit length check (consistent with the admin and shared key patterns above). * Line 1221 (/health response): new `anonymousKey` field, null when not set, the actual value when set. Admins opted into public access when they set the env var, so exposing the key here is intentional and lets ocp-connect auto-discover it without out-of-band coordination. ### package.json Version 3.6.0 to 3.7.0 (per dev iron rule 5, version bump before push). ### README.md New "Anonymous Access (optional)" subsection under Auth Modes: * Enable example (export PROXY_ANONYMOUS_KEY=...) * Client-side /health discovery explanation * Security note: opt-in to public access, rate-limit warning * "Not a secret" note: /health is unauthenticated, the key is publicly readable by design; treat it as a convenience handle, not as an access credential. ## Test evidence Offline tests on macOS 13, local server on 0.0.0.0:8889 with PROXY_ANONYMOUS_KEY=ocp_public_anon_TEST, CLAUDE_AUTH_MODE=multi, CLAUDE=/bin/echo (mock): * GET /health -> authMode: multi anonymousKey: ocp_public_anon_TEST (pass, field exposed correctly) * POST /v1/chat/completions with Bearer ocp_WRONG_KEY from 172.16.2.29 (non-localhost) -> HTTP 401 in 15ms body: Unauthorized: invalid or revoked API key (pass, validateKey still rejects unknown keys) * POST /v1/chat/completions with Bearer ocp_public_anon_TEST from 172.16.2.29 -> curl hangs at 3s after auth middleware (pass, auth passed, request reached Claude handler which hangs because CLAUDE=/bin/echo cant serve a real chat; the point is the auth middleware accepted the key, confirmed by no 401 return) * POST /v1/chat/completions with no Authorization from 172.16.2.29 -> curl hangs at 3s after auth middleware (pass, pre-existing empty-token anonymous path not regressed) node --check server.mjs: syntax OK. ## Code review One independent opus reviewer. Verdict: PASS WITH CONCERNS, zero blockers. Two strong-recommend items addressed in this commit: 1. Localhost branch was not covered in the first draft. Reviewer pointed out that a localhost client using the anon key would be labeled "local" instead of "anonymous" in stats, making operations visibility worse. Fixed by applying the same anonymous allowlist check in the localhost branch at line 1127-1138. 2. README security note was missing the explicit "not a secret" framing. Added a paragraph clarifying that because /health is unauthenticated, the anonymous key is publicly readable by anyone who can reach the server, which is intentional. Reviewer nits (tokenBuf3 naming, stats subcategory for header-less vs anon-key anonymous) are deferred as they do not affect correctness. ## Upstream dependencies on this commit After this PR is merged and the OCP instance at 172.16.2.30 is restarted with `PROXY_ANONYMOUS_KEY` set in the environment, a follow-up PR can add anonymous key auto-discovery to ocp-connect: * On startup, ocp-connect calls GET /health * If anonymousKey field is non-null and --key was not provided, ocp-connect automatically uses that key to seed per-agent auth-profiles for OpenClaw * User gets zero-config OCP connectivity for OpenClaw multi-agent setups, no admin coordination, no --key flag That follow-up is NOT in this PR. This PR is server-only. Co-authored-by: taodeng <taodeng@Taos-MBP> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
16 KiB
OCP — Open Claude Proxy
Status: Stable (v3.6.0) — Feature-complete. Bug fixes only.
Already paying for Claude Pro/Max? Use your subscription as an OpenAI-compatible API — $0 extra cost.
OCP turns your Claude Pro/Max subscription into a standard OpenAI-compatible API on localhost. Any tool that speaks the OpenAI protocol can use it — no separate API key, no extra billing.
Cline ──┐
OpenCode ───┤
Aider ───┼──→ OCP :3456 ──→ Claude CLI ──→ Your subscription
Continue.dev ───┤
OpenClaw ───┘
One proxy. Multiple IDEs. All models. $0 API cost.
Supported Tools
Any tool that accepts OPENAI_BASE_URL works with OCP:
| Tool | Configuration |
|---|---|
| Cline | Settings → OPENAI_BASE_URL=http://127.0.0.1:3456/v1 |
| OpenCode | OPENAI_BASE_URL=http://127.0.0.1:3456/v1 |
| Aider | aider --openai-api-base http://127.0.0.1:3456/v1 |
| Continue.dev | config.json → apiBase: "http://127.0.0.1:3456/v1" |
| OpenClaw | setup.mjs auto-configures |
| Any OpenAI client | Set base URL to http://127.0.0.1:3456/v1 |
Installation
OCP has two roles: Server (runs the proxy, needs Claude CLI) and Client (connects to a server, zero dependencies).
┌─ Server (always-on device) ─────────────────────────────┐
│ Mac mini / NAS / Raspberry Pi / Desktop │
│ Claude CLI + OCP server → bound to 0.0.0.0:3456 │
└───────────────────────┬─────────────────────────────────┘
│ LAN
┌───────────────────┼───────────────────┐
▼ ▼ ▼
Laptop Phone/Tablet Pi / Server
(client) (browser) (client)
Server Setup
Recommended: Install OCP on a device that stays powered on — Mac mini, NAS, Raspberry Pi, or a desktop that doesn't sleep. This ensures all clients always have access.
Prerequisites:
- Node.js 18+
- Claude CLI installed and authenticated (
claude auth login)
# 1. Clone and run setup
git clone https://github.com/dtzp555-max/ocp.git
cd ocp
node setup.mjs
The setup script will:
- Verify Claude CLI is installed and authenticated
- Start the proxy on port 3456
- Install auto-start (launchd on macOS, systemd on Linux)
- Symlink
ocpto/usr/local/binfor CLI access
Single-machine use — just set your IDE to use the proxy:
export OPENAI_BASE_URL=http://127.0.0.1:3456/v1
LAN mode — share with other devices on your network:
# Enable LAN access with per-user auth (recommended)
node setup.mjs --bind 0.0.0.0 --auth-mode multi
Then create API keys for each person/device:
export OCP_ADMIN_KEY=your-secret-admin-key
ocp keys add wife-laptop
# ✓ Key created for "wife-laptop"
# API Key: ocp_xDYzOB9ZKYzn...
# Copy this key now — you won't see it again.
ocp keys add son-ipad
ocp keys add pi-server
Run ocp lan to see your IP and ready-to-share instructions.
Verify:
curl http://127.0.0.1:3456/v1/models
# Returns: claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4
Client Setup
Clients do not need to install Node.js, Claude CLI, or the OCP repo. Only
curlandpython3are required (pre-installed on most Linux/Mac systems).
One-command setup — download the lightweight ocp-connect script:
curl -fsSL https://raw.githubusercontent.com/dtzp555-max/ocp/main/ocp-connect -o ocp-connect
chmod +x ocp-connect
./ocp-connect <server-ip>
If the server requires a key, pass it with --key:
./ocp-connect <server-ip> --key <your-api-key>
Or as a one-liner (no file saved):
curl -fsSL https://raw.githubusercontent.com/dtzp555-max/ocp/main/ocp-connect | bash -s -- <server-ip>
Example:
$ ./ocp-connect 192.168.1.100
OCP Connect
─────────────────────────────────────
Remote: http://192.168.1.100:3456
Checking connectivity...
✓ Connected
Remote OCP v3.6.0 (auth: multi)
Server allows anonymous access — no key needed.
Testing API access...
✓ API accessible (3 models available)
Shell config:
✓ .bashrc
✓ .zshrc
OPENAI_BASE_URL=http://192.168.1.100:3456/v1
System-level (launchctl):
✓ OPENAI_BASE_URL set for GUI apps and daemons
IDE Configuration
─────────────────────────────────────
Detected: OpenClaw (~/.openclaw/openclaw.json)
Configure OpenClaw to use this OCP? [Y/n] y
Provider name (models show as <name>/model-id) [ocp]: ocp
How should OCP models be configured?
1) Primary — use OCP by default, keep existing models as backup
2) Backup — keep current primary, add OCP as additional option
Choice [1]: 1
✓ OpenClaw configured
Provider: ocp
Models:
• ocp/claude-opus-4-6
• ocp/claude-sonnet-4-6
• ocp/claude-haiku-4
Priority: PRIMARY (default model)
Restart OpenClaw to apply: openclaw gateway restart
Running smoke test...
✓ Smoke test passed: OK
Done. Reload your shell to apply:
source ~/.zshrc
The script automatically:
- Writes env vars to all relevant shell rc files (
.bashrc,.zshrc) - Sets system-level env vars (
launchctl setenvon macOS,environment.don Linux) - Detects and configures IDEs (OpenClaw, Cline, Continue.dev, Cursor)
On macOS, launchctl setenv vars reset on reboot — re-run ocp-connect after restart.
Manual setup — if you prefer not to use the script:
export OPENAI_BASE_URL=http://<server-ip>:3456/v1
export OPENAI_API_KEY=ocp_<your-key>
Add these lines to ~/.bashrc or ~/.zshrc to persist across sessions.
Monitoring (Server-side)
# Per-key usage stats
ocp usage --by-key
# Key Reqs OK Err Avg Time
# wife-laptop 5 5 0 8.0s
# son-ipad 3 3 0 6.2s
# Manage keys
ocp keys # List all keys
ocp keys revoke son-ipad # Revoke a key
Web Dashboard: Open http://<server-ip>:3456/dashboard in any browser for real-time monitoring — per-key usage, request history, plan utilization, and system health.
Auth Modes
| Mode | Env | Use Case |
|---|---|---|
none |
CLAUDE_AUTH_MODE=none |
Trusted home network, no auth needed |
shared |
CLAUDE_AUTH_MODE=shared + PROXY_API_KEY=xxx |
Everyone shares one key |
multi |
CLAUDE_AUTH_MODE=multi + OCP_ADMIN_KEY=xxx |
Per-person keys with usage tracking (recommended) |
Anonymous Access (optional)
In multi mode, the admin can designate a single well-known "anonymous" key that bypasses validateKey() and grants public read/write access. This is useful for letting LAN users (or clients like OpenClaw multi-agent setups) connect without individual per-user keys.
Enable:
export PROXY_ANONYMOUS_KEY=ocp_public_anon # or any string of your choice
ocp start # or however you start the server
Client side: the anonymous key value is exposed via GET /health as the field anonymousKey (null when not set). Clients like ocp-connect can auto-discover and use it, so the end user doesn't need to get a personal key from the admin.
Security note: setting this env var is an opt-in to public access — anyone who can reach your OCP endpoint can use it, up to any rate limits you configure. Don't enable this on internet-exposed OCP instances without additional protection.
Not a secret: because /health is an unauthenticated endpoint, the anonymous key is publicly readable by anyone who can reach the server. That is intentional — the key exists so clients can self-configure without out-of-band coordination. Treat it as a convenience handle, not as an access credential.
Important Notes
- All users share your Claude Pro/Max rate limits (5h session + 7d weekly)
ocp usageshows how much quota remains- Keys are stored in
~/.ocp/ocp.db(SQLite, zero external dependencies) - Admin key is required for key management API endpoints
- The dashboard (
/dashboard) and health check (/health) are always public
Built-in Usage Monitoring
Check your subscription usage from the terminal:
$ ocp usage
Plan Usage Limits
─────────────────────────────────────
Current session 21% used
Resets in 3h 12m (Tue, Mar 28, 10:00 PM)
Weekly (all models) 45% used
Resets in 4d 2h (Tue, Mar 31, 12:00 AM)
Extra usage off
Model Stats
Model Req OK Er AvgT MaxT AvgP MaxP
──────────────────────────────────────────────────────
opus 5 5 0 32s 87s 42K 43K
sonnet 18 18 0 20s 45s 36K 56K
Total 23
Proxy: up 6h 32m | 23 reqs | 0 err | 0 timeout
All Commands
ocp usage Plan usage limits & model stats
ocp usage --by-key Per-key usage breakdown (LAN mode)
ocp status Quick overview
ocp health Proxy diagnostics
ocp keys List all API keys (multi mode)
ocp keys add <name> Create a new API key
ocp keys revoke <name> Revoke an API key
ocp connect <ip> One-command LAN client setup
ocp lan Show LAN connection info & IP
ocp settings View tunable settings
ocp settings <k> <v> Update a setting at runtime
ocp logs [N] [level] Recent logs (default: 20, error)
ocp models Available models
ocp sessions Active sessions
ocp clear Clear all sessions
ocp restart Restart proxy
ocp restart gateway Restart gateway
ocp update Update to latest version
ocp update --check Check for updates without applying
ocp --help Command reference
Install the CLI
# Symlink to PATH (recommended)
sudo ln -sf $(pwd)/ocp /usr/local/bin/ocp
# Verify
ocp --help
Cloud/Linux servers: If
ocp: command not found, the binary isn't in PATH. Full path:~/.openclaw/projects/ocp/ocp
Self-Update
# Check if a new version is available
ocp update --check
# Pull latest, sync plugin, restart proxy — one command
ocp update
Runtime Settings (No Restart Needed)
$ ocp settings maxPromptChars 200000
✓ maxPromptChars = 200000
$ ocp settings maxConcurrent 4
✓ maxConcurrent = 4
How It Works
Your IDE → OCP (localhost:3456) → claude -p CLI → Anthropic (via subscription)
OCP translates OpenAI-compatible /v1/chat/completions requests into claude -p CLI calls. Anthropic sees normal Claude Code usage — no API billing, no separate key needed.
Available Models
| Model ID | Notes |
|---|---|
claude-opus-4-6 |
Most capable, slower |
claude-sonnet-4-6 |
Good balance of speed/quality |
claude-haiku-4 |
Fastest, lightweight |
API Endpoints
| Endpoint | Method | Description |
|---|---|---|
/v1/models |
GET | List available models |
/v1/chat/completions |
POST | Chat completion (streaming + non-streaming) |
/health |
GET | Comprehensive health check |
/usage |
GET | Plan usage limits + per-model stats |
/status |
GET | Combined overview (usage + health) |
/settings |
GET/PATCH | View or update settings at runtime |
/logs |
GET | Recent log entries (?n=20&level=error) |
/sessions |
GET/DELETE | List or clear active sessions |
/dashboard |
GET | Web dashboard (always public) |
/api/keys |
GET/POST | List or create API keys (admin only) |
/api/keys/:id |
DELETE | Revoke an API key (admin only) |
/api/usage |
GET | Per-key usage stats (?since=&until=&hours=&limit=) |
OpenClaw Integration
OCP was originally built for OpenClaw and includes deep integration:
setup.mjsauto-configures theclaude-localprovider inopenclaw.json- Gateway plugin registers
/ocpas a native slash command in Telegram/Discord - Multi-agent — 8 concurrent requests sharing one subscription
- No conflicts — uses neutral service names (
dev.ocp.proxy/ocp-proxy) that don't trigger OpenClaw's gateway-like service detection
Install the Gateway Plugin
cp -r ocp-plugin/ ~/.openclaw/extensions/ocp/
Add to ~/.openclaw/openclaw.json:
{
"plugins": {
"allow": ["ocp"],
"entries": { "ocp": { "enabled": true } }
}
}
Restart: openclaw gateway restart
Telegram / Discord Usage
After installing the gateway plugin, use /ocp slash commands in your chat:
/ocp status — Quick overview
/ocp usage — Plan usage limits & model stats
/ocp models — Available models
/ocp health — Proxy diagnostics
/ocp keys — List all API keys (multi mode)
/ocp keys add <name> — Create a new key
/ocp keys revoke <name> — Revoke a key
Note: Terminal CLI uses
ocp <command>, Telegram/Discord uses/ocp <command>.
Troubleshooting
Requests fail or agents stuck
# Clear sessions and restart
ocp clear
ocp restart
# If using OpenClaw gateway
openclaw gateway restart
Usage shows "unknown"
Usually caused by an expired Claude CLI session. Fix:
claude auth login
ocp restart
Environment Variables
| Variable | Default | Description |
|---|---|---|
CLAUDE_PROXY_PORT |
3456 |
Listen port |
CLAUDE_BIND |
127.0.0.1 |
Bind address (0.0.0.0 for LAN access) |
CLAUDE_AUTH_MODE |
none |
Auth mode: none, shared, or multi |
OCP_ADMIN_KEY |
(unset) | Admin key for key management (multi mode) |
CLAUDE_BIN |
(auto-detect) | Path to claude binary |
CLAUDE_TIMEOUT |
600000 |
Request timeout (ms, default: 10 min) |
CLAUDE_MAX_CONCURRENT |
8 |
Max concurrent claude processes |
CLAUDE_MAX_PROMPT_CHARS |
150000 |
Prompt truncation limit (chars) |
CLAUDE_SESSION_TTL |
3600000 |
Session expiry (ms, default: 1 hour) |
CLAUDE_ALLOWED_TOOLS |
Bash,Read,...,Agent |
Comma-separated tools to pre-approve |
CLAUDE_SKIP_PERMISSIONS |
false |
Bypass all permission checks |
CLAUDE_NO_CONTEXT |
false |
Suppress CLAUDE.md and auto-memory injection (pure API mode) |
PROXY_API_KEY |
(unset) | Bearer token for shared-mode authentication |
Security
- Localhost by default — binds to
127.0.0.1; setCLAUDE_BIND=0.0.0.0to enable LAN access - 3-tier auth —
none(trusted network),shared(single key),multi(per-user keys with usage tracking) - Timing-safe key comparison — prevents timing attacks on API keys and admin keys
- Admin-only key management — creating, listing, and revoking keys requires the admin key
- Public endpoints —
/healthand/dashboardare always accessible without auth - No API keys needed — authentication goes through Claude CLI's OAuth session
- Keys stored locally —
~/.ocp/ocp.db(SQLite), never sent to external services - Auto-start — launchd (macOS) / systemd (Linux)
License
MIT
