> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Daemon

## Docs

- [About](https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/about.md): Choose a local or remote NeMo Relay daemon deployment.
- [Architecture and Startup](https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/architecture.md): Learn how coding harnesses, MCP clients, workers, and the daemon communicate.
- [Configuration and Managed Clients](https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/configuration.md): Prepare system configuration, credentials, and immutable coding-harness settings.
- [Windows Deployment](https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/windows.md): Run a daemon with Task Scheduler or a WinSW Windows service.
- [macOS Deployment](https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/macos.md): Run a local daemon with a user LaunchAgent or system LaunchDaemon.
- [Linux Deployment](https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/linux.md): Run a local daemon with a user or system systemd service.
- [Remote Linux: Deploy the Daemon](https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/remote-server.md): Deploy a Linux daemon with native HTTPS on a routed private network.
- [Remote Linux: Deploy Clients](https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/remote-clients.md): Connect Linux coding harnesses and workers to a remote daemon.
- [Operations and Troubleshooting](https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/operations.md): Verify worker-backed sessions, inspect logs, and recover daemon deployments.
- [Reference](https://docs.nvidia.com/nemo/relay/v0.10.0/daemon/reference.md): Commands, identity, lifecycle, and streaming contracts for managed daemon deployments.