A home for the agents you choose.
Planned managed hosting for Hermes Agent, OpenClaw and Paperclip, with persistent customer environments.
Planned service. No self-service deployment yet; we onboard early users by email.
- 01 Chosen runtime
- 02 Persistent environment
- 03 Your channels and work
What is planned
Built around your workload.
People and teams who want agents running beyond their laptop.
- Hermes Agent
- A candidate template for an agent with memory, skills and messaging channels.
- OpenClaw
- A candidate template for an assistant with channel connections and tools.
- Paperclip
- A candidate template for coordinating teams of agents, tasks, permissions and budgets.
How it works
We plan to provision, operate, upgrade and recover a persistent environment for the agent runtime you choose — so it keeps running when your laptop is closed.
- 01
A dedicated environment
Starts as a dedicated VM with persistent state. Tools run in a separate sandbox.
- 02
Pinned and upgraded
We pin the runtime version, apply upgrades deliberately, back it up and restore it.
- 03
Your models, your channels
Bring your own model keys, or use RedDB Models once that adapter is validated. Nothing is configured on your behalf.
Cost drivers
- Persistent compute, disk and network
- Tool sandbox time
- Model consumption and backups
Not promised yet
- Idle suspension, GPUs and support for every channel are not promised.
- Paperclip keeps its own PostgreSQL database.
- Each runtime needs isolation and recovery qualified before onboarding.
Source: planning record, as of 2026-10-04.
Related services
Connect the pieces you need.
- AI services RedDB Models A planned OpenAI-compatible model API for applications, the database and agents.
- AI services Agent Memory Persistent memory for agents, built on RedDB and planned as a managed service.
- AI services AI Storage Planned storage and sharing for plans, designs, reports and other agent artifacts.
Pricing
Plan the workload before the bill.
Hosting, tool execution and model consumption are separate cost drivers. Bring-your-own model credentials and platform consumption need qualified adapters; rates are not yet published.
Early access
Help shape Agent Hosting.
Tell us what you want to run, which models or runtimes you use, and what you need to keep. We will discuss fit and availability before any deployment.