linuxhsj / openclaw-zero-token

OpenClaw Zero Token **Use LLMs without API tokens** — log in via browser once, then call ChatGPT, Claude, Gemini, DeepSeek, Qwen (intl/cn), Doubao, Kimi, Zhipu GLM, Grok, Manus and more for free through a unified gateway. License: MIT English | 简体中文 --- Table of Contents • Overview • How It Works • Quick Start • Usage • Configuration • Troubleshooting • Roadmap • Adding New Platforms • File Structure • Security Notes • Sync With Upstream • Contributing • License • Acknowledgments • Disclaimer --- Overview OpenClaw Zero Token is a fork of OpenClaw that focuses on **removing API token cost** by driving the official web UIs (browser login) instead of paid API keys. Why Zero Token? | Traditional usage | Zero Token way | | -------------------- | ------------------------ | | Buy API tokens | **Completely free** | | Pay per request | No enforced quota | | Credit card required | Browser login only | | API tokens may leak | Credentials stored local | Supported providers | Provider | Status | Models (examples) | | ----------------------- | --------- | ---------------------------------------------------- | | DeepSeek | ✅ tested | deepseek-chat, deepseek-reasoner | | Qwen International | ✅ tested | Qwen 3.5 Plus, Qwen 3.5 Turbo | | Qwen China | ✅ tested | Qwen 3.5 Plus, Qwen 3.5 Turbo | | Kimi | ✅ tested | Moonshot v1 8K / 32K / 128K | | Claude Web | ✅ tested | claude-sonnet-4-6, claude-opus-4-6, claude-haiku-4-6 | | Doubao | ✅ tested | doubao-seed-2.0, doubao-pro | | ChatGPT Web | ✅ tested | GPT-4, GPT-4 Turbo | | Gemini Web | ✅ tested | Gemini Pro, Gemini Ultra | | Grok Web | ✅ tested | Grok 1, Grok 2 | | GLM Web (Zhipu) | ✅ tested | glm-4-Plus, glm-4-Think | | GLM Web (International) | ✅ tested | GLM-4 Plus, GLM-4 Think | | Manus API | ✅ tested | Manus 1.6, Manus 1.6 Lite (API key, free quota) | Tool calling All supported models can call **local tools** ( , , , , , etc.) so that agents can run commands, read/write workspace files, and automate the browser. | Provider type | Tools | Notes | | ----------------------------------------------------------- | ----- | ---------------------------------------------------------------------- | | Web (DeepSeek, Qwen, Kimi, Claude, Doubao, GLM, Grok, etc.) | ✅ | Inject XML tool descriptions in , parse streams. | | ChatGPT Web / Gemini Web / Manus API | ✅ | Similar via tool descriptions + multi-turn context + . | | OpenRouter / OpenAI-compatible APIs | ✅ | Uses native / . | | Ollama | ✅ | Uses native tools. | Agent file access is restricted by the configured **workspace** directory (see ). Extra features **AskOnce: one question, answers from all models.** AskOnce can broadcast a single query to multiple configured providers and show their replies side by side. --- How It Works High-level architecture DeepSeek auth flow (example) --- Quick Start > **Platforms** > > - 🍎 **macOS** / 🐧 **Linux**: follow START_HERE.md; full install/config in INSTALLATION.md. > - 🪟 **Windows**: use WSL2 and then follow the Linux steps. Install WSL2: , docs: Requirements • Node.js >= 22.12.0 • pnpm >= 9.0.0 • Chrome browser • OS: macOS, Linux, or Windows (via WSL2) Helper scripts (first-time & daily use) **Script overview (core 3 scripts):** | Script | Purpose | When to use | | ----------------------- | -------------------------- | ------------------------------------------------------------------------ | | | Start Chrome in debug mode | Step 2: open browser on port 9222 for logins + onboarding | | | Auth/onboarding wizard | Step 4/5: select provider (e.g. ) and capture credentials | | | Manage gateway service | Step 5 & daily use: / / / on port 3002 | Installation Clone the repo Install dependencies Step 1: Build Step 2: Configure authentication Follow the prompts (choose e.g. **DeepSeek (Browser Login)** and **Automated Login (Recommended)**). To add more providers later, just run again. Step 3: Start the gateway This will start the HTTP gateway and Web UI. --- Usage Web UI After the Web UI is started automatically. Open it in your browser and chat with any configured model. Switch models Use inside the chat box: List available models > **Important:** Only providers configured via are written into and shown in . The output shows: • All available providers (e.g. , , ) • Models under each provider • Currently active model • Aliases and config Example: HTTP API CLI / TUI --- Configuration Example --- Troubleshooting First run: use the onboarding wizard (recommended) The wizard will create all required directories and basic files. Fix issues: doctor command If you already ran the project but see missing-directories or similar errors: The doctor command will: • ✅ Check all required directories • ✅ Create missing directories • ✅ Fix common permission issues • ✅ Validate config file structure • ✅ Detect multiple conflicting state directories • ✅ Print detailed suggestions **Limitations:** • ❌ Does **not** create • ❌ Does **not** create • ✅ If those are missing/corrupt, rerun --- Roadmap Current focus • ✅ DeepSeek Web, Qwen intl/cn, Kimi, Claude Web, Doubao, ChatGPT Web, Gemini Web, Grok Web, GLM Web, GLM intl, Manus API — all tested • 🔧 Improve credential capture robustness • 📝 Documentation improvements Planned • 🔜 Auto-refresh for expired web sessions --- Adding New Platforms To add a new web provider you usually need: • Auth module ( ) • API client ( ) • Stream handler ( ) --- File Structure --- Security Notes • **Credential storage**: cookies and bearer tokens live in local and must **never** be committed. • **Session lifetime**: web sessions expire; you may need to re-login from time to time. • **Rate limiting**: web endpoints may enforce rate limits; they are not suited for heavy production workloads. • **Compliance**: this project is for personal learning and experimentation. Always follow each platform’s Terms of Service. --- Sync With Upstream OpenClaw This project is based on OpenClaw. To sync upstrea…