OpenClaw Launch

OpenClaw Launch is a managed hosting platform for open-source AI agents. It hosts three runtimes — OpenClaw (MIT license, 385,000+ GitHub stars), Hermes Agent by Nous Research, and Coding Harnesses for the major AI coding CLIs — and you pick one at deploy time. With OpenClaw or Hermes you configure your agent visually in the browser, click Deploy, and it is live in under 30 seconds on Telegram, Discord, WhatsApp, WeChat, Feishu or the built-in Web UI; a Coding Harness has no chat channels and gives you a browser terminal instead. Either way there is no Docker to install and no VPS to rent. Every runtime runs in its own isolated container on a real cloud machine with automatic SSL and a browser terminal; the two agent runtimes add real-time logs and a live browser view. There is a free 30-minute trial with no card required; paid plans start at $3 for the first month (Lite, then $6/mo) and $20/mo (Pro).

OpenClaw is an open-source AI agent framework (MIT license, 385,000+ GitHub stars) that runs on Telegram, Discord, or directly in your browser. It turns leading AI models into personal AI agents that can manage tasks, automate workflows, and chat across platforms. It was originally released as ClawdBot, then MoltBot, before being renamed to OpenClaw. OpenClaw Launch is the official managed hosting platform — it eliminates the 2–6 hour DIY setup by handling servers, Docker, networking, and SSL automatically. You configure visually and deploy in under 30 seconds.

OpenClaw Launch deploys two agent frameworks, and you pick one with a single click at deploy time. OpenClaw is the original framework — the broadest channel support (Telegram, Discord, WhatsApp, and browser), thousands of community skills, and the largest ecosystem. Hermes Agent, by Nous Research, is built for autonomy: persistent multi-level memory, 40+ built-in tools, and a self-improving loop — ideal for long-running agents that need to remember context across sessions. Both deploy in under 30 seconds on the same managed infrastructure, on the same plans, with SSL and channels included.

Yes — that is the third runtime, and it is not a chat agent. A Coding Harness is a managed cloud dev box with eight AI coding agents pre-installed — Claude Code, Codex, OpenCode, Aider, OpenClaude, Zero, Pi and DeepSeek Harness. Nothing to install on your own machine: you open a browser terminal and run whichever one you want by name, against a persisted /workspace. Your code and each CLI’s saved logins and config survive a reset, and Claude Code and Codex sign in with your own Claude or ChatGPT subscription so that subscription stays in control of billing. Same Lite and Pro plans as OpenClaw and Hermes, with a free trial.

No. Self-hosting OpenClaw or Hermes traditionally requires a Mac Mini ($500+) or VPS ($5–20/mo), Docker, SSH access, firewall configuration, and SSL certificate management. OpenClaw Launch eliminates all of that. Pick your framework and AI model, choose a chat platform, click Deploy — your AI agent is live in under 30 seconds. Zero infrastructure knowledge required.

OpenClaw Launch supports leading AI models: GPT-5.6 in three tiers — Sol, Terra and Luna (OpenAI), Claude Opus 4.8, 4.7, 4.6 and Sonnet 4.6 (Anthropic), Gemini 3.1 Pro, 3.5 Flash and 3 Flash (Google), Grok 4.6, GLM 5.2, MiniMax M3, Qwen 3.6 Plus, DeepSeek V4 Pro and V4 Flash, Kimi K2.6, and a free models router at no token cost. You can switch models at any time without redeploying. If you already pay for ChatGPT Plus, Pro or Team, you can connect that subscription and run GPT-5.6 with no per-token API cost.

Account creation and bot configuration are free. Deployment plans: Lite at $3/mo (first month) then $6/mo with $1 in AI credits, or Pro at $20/mo with $10 in AI credits. Annual billing brings Lite to $60/year and Pro to $200/year, each with a 30-day refund window. Both plans include managed OpenClaw or Hermes hosting, Telegram and Discord bot hosting, real-time monitoring, and automatic updates.

Yes. Cancel from your account settings at any time — no early termination fees, no cancellation process. Your instances continue running until the end of your current billing period.

Security is built into every layer. Each bot runs in an isolated Docker container with dedicated storage — fully sandboxed from other users. Gateway tokens are auto-generated using cryptographically secure random UUIDs. API keys you add are encrypted with AES-256-GCM in our database. All connections use SSL/HTTPS with automatic certificate management, and two-factor authentication is available on your account. We never use your data to train AI models.

There are three tiers. The Free Trial is $0 for 30 minutes with no credit card — web chat, free models, a built-in browser, and full command execution. The Lite plan is $3 for the first month, then $6/month (or $60/year, which works out to $5/month), and includes 1 vCPU, 2 GB RAM, 10 GB storage, one instance, and $1/month in AI credits. The Pro plan is $20/month (or $200/year, $16.67/month effective) with 2 vCPU, 4 GB RAM, 40 GB storage, up to 3 instances, and $10/month in AI credits. Both paid plans include Telegram, Discord, and WhatsApp bots, the Web UI, real-time monitoring, automatic SSL, and thousands of ClawHub skills. Annual plans come with a 30-day refund window.