Update: terminal, Slack, memory, and a smoother deploy flow

Hey everyone - quick update on DeployHermes (managed hosting for Hermes agents on Fly.io).

Since our last public release (right after we moved the stack to Vercel), we’ve been heads-down on reliability and on features people actually asked for. Here’s what’s new:

Big additions

• Terminal access — including an non-interactive terminal path (with fixes and better behavior for sessions).

• Slack support — alongside improvements to Telegram and Discord (including clearer links for chat channels in the UI).

• Agent memory — memory on the agent side, plus home + settings UI so it’s usable, not buried.

• Cron jobs — create and manage scheduled work from the product (with follow-up fixes so jobs are recognized reliably).

• Skills — surface and use skills from the dashboard, with UI polish so detection and editing feel sane.

• Sessions & env — session management, an env editor, and a config editor so you’re not SSH’ing for every tweak.

• Multi-provider & OpenCode — multiple LLM providers in settings, OpenCode provider support, fallback model settings, and fixes so model lists/restarts behave during deploys.

• Redeploy — one-click redeploy on an agent when you need a fresh machine without redoing the whole wizard.

Product & ops polish

• Smoother deploy flow — fewer dead ends; fixes for timeouts, config load, “coming soon” models in the wizard, and various deployment errors.

• Billing — fixes so active plans work correctly for deployment, and cancelled plans don’t clutter attach existing subscription.

• Branding — we’ve aligned on DeployHermes (formerly HermesHost in places).

• Analytics — Vercel Analytics and Datafast for understanding how the product is used.

We’re still tightening lifecycle edge cases (e.g. provisioning → fully running) and billing gates - if you’re self-hosting Hermes or trying hosted agents, we’d love your war stories in the replies.

What would you want next? (e.g. better logs, API webhooks, team seats, etc.)

Thanks for reading - and if you tried us before the terminal/memory wave, it’s worth another look.