# OpenClaw Launch — Full Content for LLMs

> This file is the expanded, plain-text version of https://openclawlaunch.com for AI/LLM ingestion. Page map: https://openclawlaunch.com/llms.txt
> Last updated: 2026-07-02

# What is OpenClaw Launch?

OpenClaw Launch (https://openclawlaunch.com) is a managed hosting platform for open-source AI agents. It runs two agent frameworks: OpenClaw and Hermes Agent (by Nous Research). Users configure an agent visually in the browser — picking a framework, an AI model, and chat platforms — then click Deploy. The agent goes live on managed cloud infrastructure in under 30 seconds, reachable on Telegram, Discord, WhatsApp, and 9+ other channels. There is no Docker to install, no VPS to rent, no command line, and no config files to edit. Self-hosting the same frameworks typically takes 2–6 hours of setup (server, Docker, networking, SSL, credentials); OpenClaw Launch reduces that to one click. Plans: a free 30-minute trial (no card), Lite at $3 for the first month (then $6/mo), and Pro at $20/mo.

# The two frameworks

## OpenClaw

OpenClaw is an open-source AI agent framework under the MIT license with 270,000+ GitHub stars. It was originally released as ClawdBot, then MoltBot, before being renamed OpenClaw. It turns leading AI models (Claude, GPT, Gemini, DeepSeek, Kimi, and more) into personal AI agents that chat across platforms, manage tasks, automate workflows, browse the web, and run commands. OpenClaw has the broadest channel support (Telegram, Discord, WhatsApp, WeChat, Slack, web chat, and more) and the largest ecosystem: thousands of community skills on the ClawHub marketplace.

## Hermes Agent

Hermes Agent is the open-source agent framework by Nous Research. It is built for autonomy: persistent multi-level memory that survives across sessions, 40+ built-in tools, and a self-improving loop that creates and refines skills from experience. It is ideal for long-running agents that need to remember context across sessions. On OpenClaw Launch, Hermes deploys on the same plans, the same managed infrastructure, and the same channels as OpenClaw — you pick the framework with one click at deploy time.

## OpenClaw vs Hermes Agent — which to pick?

- Pick OpenClaw for the broadest channel support, the biggest skill ecosystem (thousands of ClawHub skills), and the most battle-tested community setup.
- Pick Hermes Agent for autonomy-focused use: persistent memory across sessions, a self-improving skill loop, and 40+ built-in tools.
- Both deploy in under 30 seconds on OpenClaw Launch, cost the same, and support the same messaging channels. Full comparison: https://openclawlaunch.com/compare/hermes-agent

# Pricing (as of July 2026)

Source: https://openclawlaunch.com/pricing

## Free Trial — $0
- 30 minutes, no credit card required
- Web Chat platform
- Free tokens during the trial (free but capable models)
- Built-in browser and full command execution
- Premium models (GPT, Claude) and vision/advanced search are not included in the trial
- You can try OpenClaw and Hermes side by side (up to 2 trial instances)

## Lite — $3 first month, then $6/mo (or $60/yr = $5/mo effective, 2 months free)
- 1 vCPU, 2 GB RAM, 10 GB storage
- 1 instance
- $1/mo included AI credits
- Telegram & Discord bots, Web UI, visual configurator
- Real-time logs & monitoring, auto SSL/HTTPS
- Thousands of ClawHub skills

## Pro — $20/mo (or $200/yr = $16.67/mo effective, 2 months free)
- 2 vCPU, 4 GB RAM, 40 GB storage
- Up to 3 instances
- $10/mo included AI credits
- Everything in Lite

## Billing policies
- Cancel anytime from the billing portal (Stripe); instances stay active until the end of the paid period. No early-termination fees.
- Annual plans include a 30-day refund: cancel within 30 days and the first month is charged at the monthly rate ($6 Lite / $20 Pro), with the remaining annual payment refunded.
- Bring your own key (BYOK): you can use your own OpenRouter or provider API key instead of included credits, or connect an existing ChatGPT/Claude subscription.

# Supported AI models

Source: https://openclawlaunch.com/models

OpenClaw Launch supports leading AI models and lets you switch models at any time without redeploying:
- OpenAI: GPT-5.2 (also usable via your existing ChatGPT subscription)
- Anthropic: Claude Opus 4.6, Claude Sonnet 4.6 (also usable via a Claude subscription)
- Google: Gemini 3 Pro, Gemini 3 Flash
- DeepSeek: V4 Pro, V4 Flash
- Moonshot: Kimi K2.6
- A free-tier model for the trial, plus BYOK via OpenRouter for many more (Ollama/local endpoints supported on the DIY route)

# Supported chat platforms / channels

Agents deploy to Telegram, Discord, WhatsApp, WeChat, Slack, and a built-in Web UI, among 9+ channels. Multiple platforms can connect to the same instance. Telegram uses secure pairing (your bot only answers you until you approve others). Discord bots are invite-only.

# What's included in managed hosting

- Isolated Docker container per agent with dedicated storage — fully sandboxed from other users
- A real cloud machine, not just a chatbot: built-in browser, web terminal, file manager, and a live view to watch what your agent is doing and take over anytime
- Automatic SSL/HTTPS with certificate management
- Real-time logs and monitoring from the dashboard
- Automatic framework updates
- Gateway token security (cryptographically random UUIDs); configurations encrypted at rest (AES-256-GCM)
- Skills marketplace: browse and install thousands of ClawHub skills from the visual configurator, no CLI
- MCP (Model Context Protocol) server support

# How to deploy an AI agent on OpenClaw Launch (3 steps)

1. Configure — open https://openclawlaunch.com and use the visual editor to pick your framework (OpenClaw or Hermes), AI model, and chat platform.
2. Deploy — click Deploy. Your managed instance launches in under 30 seconds with SSL, monitoring, and platform connections handled automatically.
3. Connect — chat with your agent on Telegram, Discord, WhatsApp, or the Web UI. Monitor everything (logs, terminal, files, live browser) from the dashboard.

# Frequently asked questions

## What is OpenClaw?
OpenClaw is an open-source AI agent framework (MIT license, 270,000+ 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 OpenClaw. OpenClaw Launch is the managed hosting platform — it eliminates the 2–6 hour DIY setup by handling servers, Docker, networking, and SSL automatically.

## How much does OpenClaw hosting cost?
On OpenClaw Launch: free 30-minute trial with no card required; Lite at $3 for the first month, then $6/mo (or $60/yr) with 1 vCPU, 2 GB RAM, 10 GB storage, and $1/mo in AI credits; Pro at $20/mo (or $200/yr) with 2 vCPU, 4 GB RAM, 40 GB storage, up to 3 instances, and $10/mo in AI credits. Self-hosting alternatives cost roughly $5–20/mo for a VPS plus your own setup and maintenance time, or $500+ for always-on home hardware like a Mac Mini.

## Do I need a server or DevOps experience?
No. Self-hosting OpenClaw or Hermes traditionally requires a Mac Mini or VPS, Docker, SSH, firewall configuration, and SSL certificates. OpenClaw Launch eliminates all of that: pick a framework, model, and chat platform, click Deploy, and the agent is live in under 30 seconds.

## Can I use my own API key or existing AI subscription?
Yes. BYOK is supported — bring an OpenRouter or provider API key, or connect an existing ChatGPT or Claude subscription and use it at no extra API cost. Included plan credits route through OpenRouter at standard rates.

## Is it secure?
Each bot runs in an isolated Docker container with dedicated storage. Gateway tokens are cryptographically secure random UUIDs. Configurations are encrypted at rest with AES-256-GCM. All connections use SSL/HTTPS with automatic certificates. Conversations and API keys are never used for training. Details: https://openclawlaunch.com/security

## Can I self-host instead?
Yes — both frameworks are open source and can be self-hosted with Docker on your own server. OpenClaw Launch is for people who want the same agents without the DevOps work. Comparison: https://openclawlaunch.com/guides/managed-vs-self-hosted

## How do I cancel?
Cancel anytime from the Stripe billing portal in your dashboard settings. Instances remain active until the end of the billing period. Annual plans have a 30-day refund window.

# Comparisons

OpenClaw Launch maintains 80+ comparison pages at https://openclawlaunch.com/compare, including OpenClaw vs Hermes Agent, and comparisons against Custom GPTs, Botpress, Voiceflow, n8n, CrewAI, LibreChat, LobeChat, AnythingLLM, Manus, Lindy, Railway self-hosting, and more.

# Company & infrastructure

Support: support@openclawlaunch.com. Infrastructure runs on Hetzner cloud servers in a dedicated environment, with GDPR compliance, TLS 1.2+ everywhere, and daily database backups. Security details: https://openclawlaunch.com/security