Hermes Codex gets your AI agent running in under 5 minutes — with persistent memory, browser automation, and tool use. No Docker, no config files, no midnight debugging.
Free tier is live. Pro and Power tiers are available for serious workloads.
What's included
Browser automation, tool use, terminal, memory, and cron — pre-configured. No Docker, no StackOverflow at midnight.
Unlimited agent profiles on a single instance. Researchers, operators, specialists — no extra cost per agent.
OpenRouter, OpenAI, or Anthropic. Encrypted at rest, injected at deploy. We never see your AI spend.
Built-in dashboard with streaming. Connect Telegram, Discord, Slack, or WhatsApp — out of the box.
Run commands, view logs, manage your agent's environment directly from the browser. No SSH required.
Auto-restart on failure. Daily backups — never more than 24 hours from clean restore.
How it works
Start free, upgrade when you need more. Pay monthly with card, yearly for a discount.
Paste your OpenRouter, OpenAI, or Venice AI key once. Encrypted, injected, done.
Your agent is live in minutes — chat, terminal, monitoring. Connect Telegram or Discord and it follows you everywhere.
Use cases
Browse, code, manage files, call APIs, run cron tasks — autonomously. And it remembers what it learned last week.
Reads logs, restarts failing services, pages you only when a human is actually needed. Remembers your stack.
Give it a topic and a deadline. It browses, aggregates, and delivers a structured brief — then saves what it learned for next time.
Email triage, scheduling, API calls, spreadsheets — anything repetitive. Runs on cron while you sleep.
Feed it your docs. It resolves common tickets, escalates the hard ones, and gets smarter with every conversation.
Pricing
Dedicated compute. Unlimited agent profiles. BYO key, zero markup.
FAQ
Any model available through OpenRouter, OpenAI, Anthropic, or Venice AI. Bring your own API key — we don't add markup to your AI spend.
No. Hermes Codex handles all infrastructure — deployment, auto-restart, backups, SSL, and monitoring. You just paste your API key and start chatting.
Yes. Every plan supports multiple agent profiles. Pro gives you 3 concurrent agents, and Power gives unlimited concurrent agents — all from one instance.
Yes. The free tier is always available — no credit card required. You get 0.5 vCPU, 1 GB RAM, and 1 active agent to start building immediately.
Your agent's memory, files, and configuration are backed up daily. We never access your AI keys or conversation data. Everything is encrypted at rest.