HermesDeployable app

HermesYour AI agent that remembers

Self-hosted AI agent with persistent memory, scheduled jobs, and messaging-app access. Replaces ChatGPT Plus + Zapier.

View Source
What you get

An assistant that compounds, not resets

Persistent memory across every session

Hermes remembers who you are, your stack, your conventions, and every correction you've made. No CLAUDE.md to maintain — memory accumulates automatically as a side effect of normal use.

Self-hosted scheduled jobs

Cron tasks fire on your server while you're offline. Morning briefings, PR reviews, test runs, datasource monitoring — Hermes wakes up, runs the task with full memory access, and delivers the result wherever you want.

Reach it from anywhere

Same agent, same memory, same history — accessible from a terminal, the web UI, Telegram, Discord, Slack, WhatsApp, Signal, SMS, or email. Start on your phone, finish on your laptop.

Self-improving skills

When Hermes solves a tricky problem, it saves the approach as a reusable skill. No marketplace to browse, no plugins to install — skills emerge from your actual workflow.

Provider-agnostic models

Bring your own keys for OpenAI, Anthropic, Google, DeepSeek, OpenRouter — or pay-as-you-go through Vendo's metered proxies. Swap models any time without losing memory.

Orchestrates other agents

Need heavy lifting? Hermes can spawn Claude Code or Codex for complex tasks and bring the results back into its own memory. Long-horizon workflows without losing context.

See Hermes in action

hermes screenshot 1
hermes screenshot 2
ChatGPT Plus + Zapier
$200/mo
Hermes on Vendo
Pay as you go
What you save
No seat fees, no subscription
Every model and rate is in our public rate card.View rates
Pay-as-you-go

No subscription. Pay for what your agent actually does.

Hermes runs on your own deployment. You pay Vendo for the hosting and for any LLM tokens or messaging your agent burns through — billed per-use against your credit balance, no monthly minimums.

Pay as you gono subscription — only pay for what you use, full rate card in /pricing
  • Tokens billed pass-through at upstream cost plus our margin (OpenAI, Anthropic, Google, DeepSeek, OpenRouter)
  • Telegram, Discord, Slack, WhatsApp, Signal forwarding metered per message
  • Hosting from $29/mo for the always-on agent + scheduler container
  • Bring your own keys to pay providers directly and skip the proxy margin
  • Credits never expire — top up any amount, cancel anytime
See every model and its per-unit price.View full rate card
Ready to deploy

Launch Hermes on your own infrastructure.

Pay as you go — no subscriptions, no per-seat fees. Every model we bill through is listed in our rate card.

View rate card
FAQ

Frequently asked questions