Persistent memory and skills
Learned context and approved skills accumulate on durable storage between runs.
← All AI agents
Install Hermes Agent
Self-improving personal agentHermes Agent
Install Hermes Agent
on managed AI hosting.
Run a persistent agent with memory, reusable skills, tools, scheduled tasks, and messaging gateways. Darwa adds the managed runtime, HTTPS, persistent storage, and lifecycle tracking around it.
One-click deploymentAlways-on runtimePersistent storage
Why Hermes Agent
Memory and skills that outlive the session
Hermes Agent is designed to accumulate. Skills you approve are stored and reused, memory persists past any single conversation, and scheduled tasks let it act without being prompted.
- Interface
- Persistent autonomous agent
- Deployment
- Managed container
- Source
- Open source on GitHub
Hermes Agent features prepared for a managed deployment.
The visible capabilities come from the verified catalog entry; secrets and signed installer assets remain private to the backend.
Generated API key
Darwa mints the key at deploy time; it is never shipped in an image or shared between deployments.
Managed dashboard and gateway
The control interface and its gateway are deployed and tracked together.
HTTPS routing
A working address with a valid certificate from the first health check, no manual TLS setup.
Scheduled tasks
Recurring jobs run on the always-on runtime with no inbound request required.
Tools and messaging gateways
Approved tools and chat channels are wired into the same runtime.
What Hermes Agent talks to.
A selection of what the upstream project supports. Credentials for any third-party service are yours to add and revoke.
- OpenAI
- Anthropic
- Ollama
- Skills
- Memory
- Cron
- Webhooks
- Shell
- Browser
- Files
- Telegram
- Slack
- REST API
- Dashboard
- Tools
How Hermes persists between runs.
Memory and skills are written to durable storage, so a restart resumes an agent that still knows what it learned.
Useful starting points for Hermes Agent.
Long-running assistance
Keep the agent available beyond a local terminal or one browser session.
Reusable skills
Store approved operating instructions and skills on persistent plan storage.
Scheduled agent work
Combine tools, memory, and recurring jobs inside a tracked managed runtime.
What Darwa runs so you do not have to.
The hosting layer is the same for every agent, which is what makes a one-click install honest.
Verified manifest
Deployments run from a reviewed catalog entry rather than an arbitrary image you have to trust.
Isolated runtime
Each agent gets its own workload boundary, not a shared container with an unrelated website.
Persistent storage
Plan storage is allocated up front so application state survives restarts and releases.
Managed HTTPS
A working address with a certificate from the first health check, with custom domains where supported.
Health tracking
Runtime and resource signals come from the actual workload, so a failure is visible rather than silent.
Subscription lifecycle
Grace, suspension, retention, and restoration follow the plan instead of an untracked server.
Plans that can run Hermes Agent.
One AI Agent subscription covers the managed runtime, storage, and endpoint. Model provider usage is billed by that provider.
Live pricing is temporarily unavailable. Hermes Agent needs at least 1 vCPU, 1 GB RAM, and 10 GB of storage.
View AI agent plansFrom catalog page to a running Hermes Agent service.
- 1
Choose Install
Darwa keeps Hermes Agent selected when the authenticated launch flow opens.
- 2
Confirm a plan
Use an active agent subscription or choose a plan with enough compute and storage.
- 3
Choose an address
Start with an agents.darwa.co address or select an eligible verified custom domain.
- 4
Launch and track
The backend verifies the manifest, creates the runtime, and records its service and container identities.
Hermes Agent questions.
Darwa hosts the open-source application independently; upstream licensing and product behavior remain with its project.
What exactly is a skill?+
A skill is a reusable set of approved operating instructions the agent can apply to a recurring task. Skills are stored on the deployment's persistent volume, so they accumulate rather than being re-explained.
Does the agent act without being asked?+
It can, when you configure scheduled tasks. Any autonomous action is limited to the tools and credentials you have explicitly enabled.
How is memory different from conversation history?+
History is the transcript of one exchange. Memory is the context Hermes deliberately retains across exchanges, which is what makes an always-on deployment meaningfully different from a local session.
What credentials does it need?+
At minimum a model provider key. Anything further, such as messaging gateways or repository access, is added only if you want the agent to use it.
What does Darwa manage for Hermes Agent?+
Darwa manages the verified deployment manifest, isolated runtime, persistent storage allocation, HTTPS endpoint, health tracking, usage visibility, and paid-plan lifecycle. You manage the agent's models, credentials, tools, content, and decisions.
How do I install Hermes Agent?+
Choose Install Hermes Agent, sign in, and select an AI Agent plan if the workspace does not already have one. The launch flow keeps Hermes Agent selected while you choose its address and start the managed deployment.
What resources does Hermes Agent require?+
The current catalog minimum is 1 vCPU, 1 GB RAM, and 10 GB of storage. Real requirements depend on concurrency, models, document volume, integrations, and enabled features.
Does Hermes Agent data survive restarts?+
Darwa allocates persistent storage according to the selected plan. Important application data should still follow the backup and recovery practices required by your business.
Can Hermes Agent use a custom domain?+
The application can start with a managed Darwa address. A domain you own can be selected when custom-domain support is available for the launch flow and its DNS is verified.
Is Darwa affiliated with Hermes Agent?+
No affiliation is implied. Hermes Agent is a third-party open-source project. Darwa provides independent managed hosting and links to the upstream repository for project information and licensing.
Ready when you are
Sign-in and an active Darwa AI Agent plan are required before deployment.Deploy Hermes Agent in one click.
Sign in, pick a plan with enough resources, and Darwa builds the managed runtime around it.
