awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
linuxhsj avatar

linuxhsj/openclaw-zero-token

0
View on GitHub↗

Openclaw Zero Token

OpenClaw Zero Token is a self-hosted gateway and assistant platform that lets people chat with browser-based AI services such as ChatGPT, Claude, Gemini, DeepSeek, Kimi and Grok without paying for API tokens. It captures a login from a debuggable Chrome browser through the Chrome DevTools Protocol, then reuses that session's cookies and headers for later requests. A single OpenAI-compatible chat completions endpoint, secured by a bearer token, routes each request to whichever web model is configured, so outside programs can call those models like a standard API.

Because web chat models have no native function calling, the project injects tool definitions into the prompt and parses the replies, which lets those models run local actions such as search, fetch, exec, read, write and message. It also provides tooling for managing the browser logins: a guided sign-in across multiple platforms, status checks, and re-authentication when sessions expire. Users can attach to either a dedicated debug browser or one they start themselves. Replies stream back progressively, and a question can be sent to several providers at once to compare answers, or the model can be switched mid-conversation with a slash command.

Beyond web models, the assistant connects to messaging platforms including Discord, Slack, Telegram, iMessage and Nostr. Conversations are bound to stable sessions and threads, with per-session and per-channel model overrides. Access is controlled through sender allowlists, direct-message policies, device pairing and human approval of command execution. A plugin system covers providers, channels, search tools and hooks, and skills extend the assistant further. Scheduled and cron-based agent jobs, webhook mapping, and delivery of results to chosen channels cover automation. Media handling (images, audio, video, PDFs), speech transcription and wake-word triggers round out the surface. API-key and local providers such as Ollama, SGLang, MiniMax and cloud-hosted models are also supported.

The daemon reloads configuration live and can be installed as a background service on macOS, Linux and Windows. Install scripts for Linux, macOS and Windows are provided, along with Docker, Podman, Kubernetes and systemd setups. A browser-based control interface and chat UI are included.

Features

  • AI Service Gateways - Acts as a gateway routing chat requests to browser-based AI services such as ChatGPT, Claude, Gemini, DeepSeek and Kimi using reused logged-in sessions.
  • Browser Session Token Reuse - Reuses a logged-in browser session's cookies and headers to reach web AI models like ChatGPT, Claude and Gemini without paid API tokens.
  • Browser Session Attachments - Attaches to a debuggable Chrome instance over the DevTools Protocol and reuses its logged-in cookies and headers to reach web AI chat services without API keys.
  • OpenAI-Compatible APIs - Exposes an OpenAI-format chat completions endpoint secured by a bearer token so outside programs can call any configured web model.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI
5,213 stars·1,223 forks·TypeScript·MIT·1 view
  • OpenAI-Compatible Endpoints - Exposes a standard chat completions endpoint behind a bearer token and routes each request to the configured web model provider.
  • Local Tool Call Parsing - Injects tool definitions into prompts and parses model replies so web chat models lacking native function calling can run local actions.
  • Model Provider Routing - Routes messages from any connected channel to the configured web model provider, then continues the normal conversation, tool and reply flow.
  • AI Gateways - Runs a self-hosted gateway that serves an OpenAI-compatible endpoint, manages provider sessions, credentials and plugins, and runs as a background service.
  • Token-Free Web Model Access - Lets users chat with Claude, ChatGPT, Gemini, DeepSeek, Kimi and Grok by reusing a browser login rather than paying for API tokens.
  • AI Chat Services - Connects users to browser-based AI chat services such as ChatGPT, Claude, Gemini, DeepSeek, Kimi and Grok without paying for API tokens.
  • Authentication Session Reuse - Reuses an authenticated browser session so many web AI chat models can be called through one gateway without paid API tokens.
  • Existing Session Reuse - Authenticates to model websites using the existing browser's cookies, headers and in-page requests instead of paid API credentials.
  • Chrome DevTools Protocol Sessions - Connects to a debuggable Chrome through the DevTools Protocol and reuses saved profiles to keep web model sessions authenticated.
  • Recurring Agent Scheduling - Runs agent jobs on fixed intervals, one-shot times or cron expressions, with staggered starts and catch-up after restarts.
  • Tool Execution Approvals - Forwards command execution requests to a person for review and returns the decision so risky actions run only after explicit approval.
  • Cross-Model Comparators - Broadcasts one question to several configured providers at once and shows their replies side by side for comparison.
  • Model List Management - Lets users switch the active model with an in-chat command and list configured providers, models, aliases and the current model.
  • Model Response Streaming - Relays web model replies in small chunks as they arrive so answers appear progressively and flow into session and tool handling.
  • Multi-Model Answer Comparisons - Broadcasts a single question to several AI providers at once for side-by-side answer comparison, and lets users switch models mid-conversation with a slash command.
  • Multi-Model Response Comparators - Sends one question to several AI providers at once through a command-line plugin so users can compare answers side by side.
  • Per-Channel Model Overrides - Lets each channel or conversation use its own AI model instead of the global default through configurable model overrides.
  • Per-Session Provider Overrides - Lets a single conversation pick a different AI model or reasoning level than the default, applying only to that session.
  • Personal AI Assistants - Provides a personal assistant that connects many model providers and messaging channels, with plugins, skills, scheduled jobs and tool calling for web models.
  • Tool Calling - Injects tool definitions into prompts and parses replies so web chat models without native function calling can run search, fetch, exec, read, write and message actions.
  • Multi-Platform Bot Gateways - Runs a background service connecting AI models to Discord, Slack, Telegram and Nostr, with device pairing, sender allowlists and approval controls.
  • Live Configuration Reloads - Detects configuration file changes and computes a reload plan so the running daemon applies new settings without restarting.
  • Chat Platform Integrations - Provides platform-specific helpers for Discord, Feishu and BlueBubbles covering account handling, message sending, session keys, thread bindings and timeouts.
  • Messaging Channel Connections - Registers and configures chat platforms such as Discord, Slack and Telegram, tracking account status and targets for sending and receiving messages.
  • Background Service Hosting - Registers the assistant as a managed background service on macOS launchd, Linux systemd and Windows scheduled tasks so it starts automatically.
  • Authentication Login Handlers - Captures a one-time browser login for each AI provider and reuses that session for later requests instead of requiring an API key.
  • Command Allowlists - Matches commands against permitted patterns so only pre-approved programs run without further confirmation.
  • Session Authentication - Checks saved provider login status and re-authenticates expired sessions so web model access keeps working without interruption.
  • Chat Sender Allowlists - Matches incoming senders against configured allowlists so only approved users or accounts can interact with the assistant on a channel.
  • Web Sign-in Flows - Walks users through signing in to many web chat services in turn so each platform's session is captured for later use.
  • Plugin Extenders - Loads bundled and optional extensions from a dedicated directory so users can add providers, channels, and tools without changing the core.
  • Provider Plugins - Ships providers, channels, search tools and hooks as discoverable plugins with manifests and configuration schemas registered at runtime.
  • Chat Channel Integrations - Connects the AI assistant to messaging platforms such as Discord, Slack, Telegram, iMessage and Nostr so people can chat with it from familiar apps.
  • Messaging Platform Connectors - Connects the assistant to external messaging services such as BlueBubbles so users can converse with it from apps they already use.
  • Web-Based Control Panels - Hosts a browser-based control panel over HTTP with security headers and request routing for managing the assistant.
  • AI Model Routing Strategies - Routes user messages to the web versions of major AI models and returns their replies without needing each vendor's official API key.

    • Star history

    Star history chart for linuxhsj/openclaw-zero-tokenStar history chart for linuxhsj/openclaw-zero-token

    How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

    Projects sharing features with Openclaw Zero Token

    These projects share indexed features with Openclaw Zero Token. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
    • citrolabs/ego-litecitrolabs avatar

      citrolabs/ego-lite

      22,011View on GitHub↗

      Ego Lite is a browser automation tool built for AI coding agents. It lets agent command-line tools such as Claude Code, Codex, and Cursor open pages, read their content, fill forms, click, and scrape the web from plain-language requests, working inside the user's real browser. Browser actions are exposed as callable JavaScript functions, so an agent can chain a whole multi-step task into one script rather than issuing many separate tool calls, which reduces time, token use, and cost. Agents act inside the user's existing browser profile, with access to current logins, cookies, and open tabs,

      JavaScriptagent-skillsai-agentautomation
      View on GitHub↗22,011
    • ogx-ai/ogxogx-ai avatar

      ogx-ai/ogx

      8,454View on GitHub↗

      OGX is a self-hostable API server that exposes OpenAI-compatible endpoints for chat completions, responses, and embeddings, and routes them to many local or hosted model backends. It also accepts requests from Anthropic Messages and Google GenAI client libraries, translating them into one native format so teams can keep the client libraries they already use. The same core can run as an HTTP server reachable from any language or as a library imported into a Python program. What sets it apart is that agent orchestration runs on the server. Tool calling, connections to MCP tool servers, file sea

      Python
      View on GitHub↗8,454
    • builderz-labs/mission-controlbuilderz-labs avatar

      builderz-labs/mission-control

      6,461View on GitHub↗

      Mission Control is a self-hosted web dashboard that acts as a control plane for autonomous AI coding agents. It lets operators register and monitor a fleet of agents across runtimes, dispatch tasks to them, review their runs, and track token spend, all from one interface backed by role-based access and an audit log. Work reaches agents through priority queues, direct assignment, cron-driven recurring templates, and multi-step pipelines that chain one agent's output into the next. Agents claim the highest-priority task atomically, and completed work can be routed through a quality-review gate

      TypeScriptagent-observabilityagent-operationsagent-orchestration
      View on GitHub↗6,461
    • 1186258278/openclawchinesetranslation1186258278 avatar

      1186258278/OpenClawChineseTranslation

      3,795View on GitHub↗

      OpenClawChineseTranslation is a framework for building conversational assistants that functions as a cross-platform chat gateway. It synchronizes conversational data between multiple external messaging applications and a centralized core, allowing users to interact with an assistant across different platforms. The system utilizes a plugin-based extension architecture to integrate external services such as note-taking and password managers. It features a model-agnostic provider interface, which enables the underlying intelligence to be swapped by selecting different large language model provid

      JavaScriptai-assistantchatbotchinese
      View on GitHub↗3,795
    Compare all 30 related projects→

    Frequently asked questions

    What does linuxhsj/openclaw-zero-token do?

    OpenClaw Zero Token is a self-hosted gateway and assistant platform that lets people chat with browser-based AI services such as ChatGPT, Claude, Gemini, DeepSeek, Kimi and Grok without paying for API tokens. It captures a login from a debuggable Chrome browser through the Chrome DevTools Protocol, then reuses that session's cookies and headers for later requests. A single OpenAI-compatible chat completions endpoint, secured by a bearer token, routes each request to…

    What are the main features of linuxhsj/openclaw-zero-token?

    The main features of linuxhsj/openclaw-zero-token are: AI Service Gateways, Browser Session Token Reuse, Browser Session Attachments, OpenAI-Compatible APIs, OpenAI-Compatible Endpoints, Local Tool Call Parsing, Model Provider Routing, AI Gateways.

    Which projects share features with linuxhsj/openclaw-zero-token?

    Projects with overlapping indexed features include: citrolabs/ego-lite — Ego Lite is a browser automation tool built for AI coding agents. It lets agent command-line tools such as Claude… ogx-ai/ogx — OGX is a self-hostable API server that exposes OpenAI-compatible endpoints for chat completions, responses, and… builderz-labs/mission-control — Mission Control is a self-hosted web dashboard that acts as a control plane for autonomous AI coding agents. It lets… 1186258278/openclawchinesetranslation — OpenClawChineseTranslation is a framework for building conversational assistants that functions as a cross-platform… paddlepaddle/fastdeploy — FastDeploy is a high-performance deployment framework for large language models, vision models, and multimodal models.… open-jarvis/openjarvis — OpenJarvis is a local-first personal AI assistant and agent framework. It runs language models on a user's own laptop,…