Coming from Hermes Agent?
Hermes Agent is Nous Research’s MIT-licensed agent: skills it writes for itself, subagents, a scheduler, a webhook gateway, and hosting either on your own machine or on Hermes Cloud. Hermes can also write and schedule script-only jobs that make no model call. Whenever is the narrower option for jobs whose steps you already know: you describe one in plain language, AI writes TypeScript, and from then on the run is code that Whenever hosts. AI building is free within weekly usage limits; the file is yours. Review summaries and sample results; reading code is optional. Fixed logic is deterministic with the same inputs and dependencies, while changing external data and optional AI can change results and costs.
What you get on Whenever
Hosted by Whenever
Whenever runs published workflows for you, with managed credentials for supported connections and stored secrets for other APIs. Hermes Cloud also provides managed hosting; compare the workflow and deployment you need.
TypeScript you review before it runs
You describe the job and AI writes the TypeScript. From then on the run is the published code, so the same inputs and the same rules reach the same destinations every time. This applies to fixed non-AI logic with the same inputs and dependencies; optional AI and changing external state can change outcomes. You can review the summary and results without reading code.
A run counts once
A published execution counts as one run within its call budget. AI steps draw on the plan’s included runtime AI spend and external services may bill separately. Building has weekly limits; at a run or AI-spend limit, contact Whenever about a larger plan.
A concrete decision
Illustrative scenarios, not customer results or recorded runs.
Greg: no “done” without the invoice receipt
Illustrative decision, not a recorded customer run: Greg wants each paid order checked against Stripe, then an invoice created, its ID saved, and only then a confirmation sent. He specifies that an invoice failure must stop the confirmation, and an already-handled order must not be charged or invoiced again. He checks the summary, sample records, provider receipts and run history—not source code. Test a missing payment, a failed invoice and a duplicate event before publishing. Whenever fits when those prescribed steps matter more than an agent deciding them again; a fixed workflow elsewhere can fit too. No screenshot here claims these actions were actually delivered.
Jaunius: make the edge cases explicit
Illustrative decision, not a benchmark: Jaunius needs all pages of 5,000 contacts, a saved last-seen ID, updates only for changed records and a clear record of which writes failed. He brings the old workflow and sample inputs, reconnects accounts, and tests pagination, an API failure and a repeated event before switching triggers. Choose a single procedure if it makes this logic easier to maintain; the other tools can also support complex logic. An optional model that classifies a note can vary and adds runtime AI usage. Compare the monthly subscription and actual usage, not the number of steps alone.
Self-hosted or Hermes Cloud, or a run allowance.
Hermes supports self-hosting and managed Cloud. Cloud compute and storage usage are billed daily, with inference and tools separate; script-only jobs need not call a model. Whenever provides managed runs with optional runtime AI.
Hermes Agent
Open source + hosting
Hosting usage, plus model and tool usage where used
MIT software. Hermes Cloud documents compute metered by actual uptime and storage, billed daily; inference and tool usage are separate.
Self-hosting involves your machine and configured providers. Hermes Cloud bills daily for compute metered to actual uptime plus storage; stopped instances still use storage. Inference and tool usage are separate. A daily billing cycle is not a fixed daily instance price. Script-only jobs need not call a model.
A run is one execution of one workflow, start to finish. AI building and editing are free within weekly usage limits; runs are metered separately.
A closer look
What changes when you describe the job in plain language and code runs it: to build, to run, and to keep.
Repeatable execution logic
Hermes Agent
A scheduled job normally starts a fresh agent session each time it is due. The docs also describe a script-only mode that runs with no LLM involvement at all, which is as fixed as any script you write.
Whenever
AI writes it, then published code runs the same execution logic. With identical inputs and dependencies, non-AI logic is deterministic. Changing API data, time, randomness or an optional model step can change results; this is not an exactly-once delivery guarantee.
Runs per dollar
Hermes Agent
Budget your deployment and provider usage. Hermes Cloud documents usage-based compute and storage billed daily, plus separate inference and tool usage; this is not one universal per-run price.
Whenever
Pro includes 10,000 runs per month; see the pricing page for current US dollar prices. AI building and editing are free within weekly usage limits. Published runs are metered separately: the meter counts the whole run, not individual steps. External services and optional model calls can have their own charges.
What you can express
Hermes Agent
Hermes documents skills, terminal and file tools, local models and delegated agents. Ten concurrent subagents is a documented default, not a universal ceiling; structured results can still report schema-validation failure.
Whenever
Describe the rules you already know; AI writes the procedure. Review the summary and sample results, not necessarily the code. Keep an explicit model step for judgment. Agent platforms may also offer fixed workflows or scripts; compare the mode you actually use.
Export and portability
Hermes Agent
Hermes provides MIT source and file-based skills. Profile git distributions and tarball exports have different contents: credentials are filtered by filename, and git distributions do not include user memories or sessions. Check the chosen export format before moving a profile.
Whenever
The TypeScript is yours: read it, edit it, export it, take it with you. Moving it to another runtime can require adapting managed connections, triggers and runtime-specific integrations.
Debugging a failed run
Hermes Agent
A durable execution ledger, separate statuses for a failed run and a failed delivery, incident records, a doctor command, and preflight validation, on by default, that refuses to dispatch a misconfigured job rather than spending tokens on it.
Whenever
Read the procedure and the execution log together, then re-test the failing input. Reproduce with safe inputs; changing external state can change the failure.
Where the AI cost lands
Hermes Agent
A scheduled agent turn calls the configured model when it fires. Script-only jobs, delivery-only webhook routes, skipped pre-checks and blocked configurations need not make a model call; model and tool costs depend on the configured work.
Whenever
AI writes the workflow once, with free building subject to weekly AI usage limits. A published procedure runs its steps without a model choosing them. Any model call you explicitly include still runs and has its own cost.
When to keep Hermes Agent
Hermes Agent
Consider Hermes for agent research, skills, local files or local models. Self-hosting alone does not guarantee that no data leaves a machine: configured models, tools and network access determine that.
Whenever
Consider Whenever for a stable API procedure you want as a reviewable, hosted workflow. Keep an optional model step where judgment helps; that step can vary and uses runtime AI.
Where it runs
Hermes Agent
Hermes supports self-hosting and Hermes Cloud. Self-hosting means operating the machine; Cloud advertises managed hosting. Confirm which secrets, updates and backups each deployment leaves to you.
Whenever
Whenever runs published workflows for you, with managed credentials for supported connections and stored secrets for other APIs. Complete connection setup and review access permissions before publishing.
Sources and scope
Official sources captured on the date shown below. These describe published features and billing rules, not independent performance tests. Check the linked documentation for current modes, plans and limits. No competitor dollar price is asserted.
Checked
- Script-Only Cron Jobs (No LLM) | Hermes Agent
- Scheduled Tasks (Cron) | Hermes Agent
- Hermes Cloud — Always-On AI Agent Hosting | Nous Research
- Webhooks | Hermes Agent
- GitHub - NousResearch/hermes-agent: The agent that grows with you · GitHub
- Skills System | Hermes Agent
- Profile Distributions: Share a Whole Agent | Hermes Agent
- Subagent Delegation | Hermes Agent
- Local Models | Hermes Agent
Assistants that live in a chat app
Starter briefs for related jobs, not recorded runs. Connect authorised accounts, confirm trigger and plan requirements, then review and test the workflow before publishing.
Build this workflowAsk a Telegram bot for your agenda and inboxReplies to /today with your calendar and open tasks and to /inbox with a one-line summary of each unread email. After publishing, you pick a secret token in Whenever and pass it with the webhook address to Telegram's setWebhook; one bot serves one workflow.
Build this workflowSchedule Telegram channel posts from a sheetPublishes due rows from your posting sheet to Telegram on the cadence you choose, then marks each row Posted.
Build this workflowGet Telegram alerts on big price movesChecks your tickers every hour and messages you on Telegram when one moves more than your threshold within that hour.
Build this workflowCollect leads in a Telegram bot conversationAsks for name, email, phone and company one question at a time, keeps the answers in a sheet, and adds each finished lead to HubSpot. After publishing, you pick a secret token in Whenever and pass it with the webhook address to Telegram's setWebhook; one bot serves one workflow.
Build this workflowSend yourself a morning digest on TelegramDelivers one Telegram message each morning with your unread email, today's meetings and the tasks due.Build this workflowStart with one scheduled Hermes job.
Keep Hermes where it serves you well. Describe one recurring job, and Whenever writes it as hosted code you can read.
Pick a job whose prompt stopped changing
Choose a cron job you no longer edit. Record its schedule, the skills it attaches, the tools it touches and where its output is delivered.
Describe the procedure, not the prompt
Say what the job does in terms of inputs, rules and destinations, and Whenever’s AI writes that as TypeScript. Review the workflow summary and sample results; inspect TypeScript if useful and reconnect each service; skills and local file access do not transfer to a hosted runtime.
Run both, then pause the job
Compare results on real inputs, including the failure cases. Pause the Hermes job before publishing the new trigger so the same work is not delivered twice.