Developers
Deploy the agent you’ve built.
Run a Hermes agent in the cloud. Connect tools and model providers, then test your workflow.
Explore developer hostingcloudrun
Deploy any AI agent in 60 seconds.
For developers, automation builders, and agencies running agents for clients. Configure tools, channels and schedules from one workspace.
Get startedAgents reach the tools you already run
Bring your own AI
Use the AI plan you already pay for
Your agents run on your ChatGPT subscription or your own provider key. No per-token bill from cloudrun, and no platform key ever touches your box.
Connect the plan you already pay for
Sign in with ChatGPT and your agents run on that subscription. The work bills to your plan, not to us.
Or paste a provider key
Anthropic, OpenAI and every other provider the runtime speaks to. The key is configured on your box, in the Models panel.
Start on the free tier
New agents run on the runtime's free tier from the first minute. Connect a plan when you want a stronger model.
A different model per agent
Each agent picks its own. Put drafting on the model that writes best and analysis on the one that reasons best.
Provisioning
Start from a prepared runtime
Boxes do not install a toolchain at provision time. A golden snapshot is baked ahead of the request, and standing up a project restores it.
Create the project
- Project created — seat reserved before anything boots
- Box requested — isolated machine, one per project
Restore the runtime
- Snapshot restored — runtime and browser already baked in
- Runtime configured — driven over its own dashboard API
Agent online
- Agent online — canvas ready, free model tier live
A control plane, not another runtime
Your agents run on their own box. cloudrun stands it up, configures it, and gives you one place to watch the whole fleet.
Your keys, your models
Agents start on the runtime's free tier. Connect your own providers when you want stronger ones.
Open AI
GPT 5
Connected
All Models69,420
Claude 4 Opus
Unavailable
✨
✨
✨
✨
✨
✨
✨
✨
ChatGPT
Connected
✨
✨
✨
✨
✨
✨
✨
✨
Llama 3.2
Waiting
✨
✨
✨
✨
✨
✨
✨
✨
Reachable where you work
Telegram, Slack, email and more. A channel is configuration on the agent, not a rewrite.
One canvas over the fleet
Organization, project, engine, agent. Every node on one canvas you arrange, instead of a dashboard per agent.
A box per project
Every project gets its own isolated machine. Separate agents, separate tools, separate blast radius.
Automations on a cron
Scheduled prompts run on their own timer. The agent wakes up, does the work, and reports back.
Paused, then reclaimed
A lapsed subscription pauses the fleet and keeps it for 30 days before anything is deleted.
Build agents. Put them to work.
Automation engineers
Put recurring work on a schedule.
Connect supported apps, define the task and schedule it from the dashboard.
Explore automation workflowsAgencies
Deliver agents for your clients.
Set up a client project, test the result and prepare the handoff for the service you sell.
Explore agency hosting
One contract, room for every runtime
An engine kind brings its own substrate, its own panels and its own API namespace. There is no plugin registry to satisfy, so adding the next one is wiring, not a rewrite.
OpenClaw
Wired as an engine kind. Coming soon.
Codex
Wired as an engine kind. Coming soon.
Claude Code
Wired as an engine kind. Coming soon.
Available now
Project created
Hermes
Profiles with a soul, skills, tools, channels, automations and memory. Available now.
Skills
Tools
Channels
OpenCode
Wired as an engine kind. Coming soon.
Pi
Wired as an engine kind. Coming soon.
Cursor
Wired as an engine kind. Coming soon.
Pricing
You pay for running deployments
Not for members, not for projects, not for a tier you grew out of. The subscription quantity always equals the number of deployments actually running.
Cloud
per agent, per month
$49
We run the boxes. Add agents anytime; from your second agent, every agent drops to $39.
- An isolated box per project
- Hermes provisioned from a prepared runtime image
- Free model tier to start, your own keys when you want more
- Channels, automations and memory on the agent
- One canvas over the whole fleet
How the meter works
Per deployment- You only pay for the time an agent runs — add mid-month, pay the remainder
- Delete anytime — unused time is credited back automatically
- Members are free; you're billed only for running agents
Isolation
A box per project
No. It is a control plane, not a runtime. Your agents run on their own box, and their skills, channels, automations and transcripts live there. cloudrun provisions the box, configures it, and stores only what it needs to reach it.
Read the docs- Available runtime
- Hermes
- Box per project
- 1
- Engine kinds wired
- 7
- Fleet kept after a lapse
- 30 days
FAQs
Questions, answered
What the control plane does, what it does not, and what you are charged for. Anything missing is in the docs.
No. It is a control plane, not a runtime. Your agents run on their own box, and their skills, channels, automations and transcripts live there. cloudrun provisions the box, configures it, and stores only what it needs to reach it.
cloudrun
Your first agent is one project away
Create a project, configure Hermes, and test the first task your agent will handle.