Run Hermes Agent with Local Models

Verify your environment

Before installing Hermes, confirm that your DGX Spark is running DGX OS, has network access, and exposes the basic command-line tools used during install.

uname -a
curl --version
git --version

What to look for: DGX Spark ships with DGX OS, which is a specialized Ubuntu-based Linux image. The uname -a line will not always contain the literal string “DGX OS”. A healthy Spark typically shows Linux, Ubuntu, and nvidia (kernel or platform identifiers) in that output. Confirm that curl --version and git --version print version lines without errors.

Verify outbound HTTPS to Telegram (gateway requirement)

The Hermes Telegram gateway talks to Telegram’s cloud API over HTTPS. On some corporate or lab networks, outbound HTTPS to api.telegram.org is blocked, which produces a working local install but a bot that never responds. Before you invest time in gateway setup, run this quick check from the same network you will use for the Spark:

curl -sS --connect-timeout 10 -o /dev/null -w "HTTP %{http_code}\n" https://api.telegram.org/

You should see an HTTP status line such as HTTP 404, HTTP 200, or HTTP 302 (Telegram’s edge often answers bare GET requests with a short JSON or redirect). The important part is that the request completes over TLS without hanging. Timeouts, “Could not resolve host”, or connection refused mean the gateway will not reach Telegram from this network—try a path that allows that traffic (for example a personal hotspot) or ask your network administrator to allow HTTPS to api.telegram.org.

Serve a model with vLLM

Hermes will be configured against a local, OpenAI-compatible endpoint, so a model server must be running before you launch the Hermes installer. This playbook uses vLLM with the agent-ready nvidia/Qwen3.6-35B-A3B-NVFP4 recipe — the same one documented in the vLLM playbook's Run Agent Ready Qwen3.6 35B Model with vLLM tab.

Follow that tab to launch the server in a separate terminal on the Spark so it can run alongside Hermes. It serves nvidia/Qwen3.6-35B-A3B-NVFP4 on an OpenAI-compatible API at http://localhost:8000/v1.

Once the server reports Application startup complete, verify the API on 8000 in another terminal. A healthy server returns JSON with a top-level "data" array listing the served model:

curl -sS http://localhost:8000/v1/models

You should see nvidia/Qwen3.6-35B-A3B-NVFP4 in the returned list.

Install Hermes

The steps below were verified against Hermes Agent v0.18.0 (2026.7.1) · upstream 676236bb. Newer installer versions may word prompts differently or reorder them; follow the closest matching prompt.

Run the installer from an interactive terminal on the Spark. If you are connected over SSH, use a normal SSH session where you can answer prompts and enter your sudo password when requested. If you run the installer from a non-interactive automation shell, Hermes can install but the setup wizard and optional system-package prompts may be skipped; use the Non-interactive SSH fallback below in that case.

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

The installer walks you through an interactive setup wizard. This playbook uses the Blank Slate path, which keeps the wizard short — basics, model endpoint, and terminal backend — and then configures Telegram afterwards with a single hermes gateway setup command (Step 3e). The subsections below follow the wizard's prompt order.

3a. Installer basics

1. "Install ripgrep for faster file search ffmpeg for TTS voice messages? [Y/n]" — Press Enter to accept the default and install both helpers. If sudo asks for your password, enter your Linux user password. If you skip this step or run without a terminal, Hermes still works, but file search falls back to slower tools and TTS voice-message support is limited. You can install the helpers later with sudo apt install -y ripgrep ffmpeg.

2. "How would you like to set up Hermes?" — Choose Blank Slate. It starts with everything off except the bare minimum, still offers the provider prompts used in the rest of this step, and lets you opt in to individual capabilities later. For context on the other options: Quick Setup does not offer provider selection — it signs in through https://portal.nousresearch.com (registration or login required) instead, so it won't point Hermes at the local model endpoint on your DGX Spark — and Full setup walks through every provider, tool, and plugin option — this playbook uses Blank Slate to get users started quickly.

3b. Point Hermes at your local model

1. "Select provider" — The wizard lists many hosted providers; scroll past them and choose Custom endpoint (enter URL manually) so Hermes can be pointed at the model endpoint running on your DGX Spark. (If the machine already has saved endpoints, entries like Local (localhost:8000) appear near the bottom of the list — selecting the matching saved entry works too.)

2. "API base URL [e.g. https://api.example.com/v1]:" — If this prompt appears, enter the URL of your local model server. For the local vLLM endpoint from Step 2, use http://localhost:8000/v1. (Depending on installer version or prior config, this question is sometimes skipped when the endpoint is already inferred—continue with the prompts you do see.)

3. "API key [optional]" — Leave blank and press Enter; vLLM does not require a key for a local model.

4. Model selection — The installer lists the models served by your local endpoint (vLLM reports these via /v1/models). Select nvidia/Qwen3.6-35B-A3B-NVFP4.

5. "Context length in tokens [leave blank for auto-detect]:" — Press Enter to let Hermes auto-detect the context length from the served model (the recipe serves --max-model-len 262144).

6. "Display name [Local (localhost:8000)]" — Press Enter to accept the suggested label, or type a custom name to identify this endpoint in the Hermes UI.

Non-interactive SSH fallback: If the installer prints "Setup wizard skipped (no terminal available)", or if you are validating the playbook through non-interactive SSH, configure the local vLLM endpoint with Hermes' config command instead of the prompts above:

export PATH="$HOME/.local/bin:$PATH"
hermes config set model.provider custom
hermes config set model.base_url http://localhost:8000/v1
hermes config set model.default nvidia/Qwen3.6-35B-A3B-NVFP4
hermes -z "Reply exactly HERMES_OK"

The last command should return HERMES_OK, confirming that Hermes can call the local vLLM model without opening the TUI.

3c. Choose the terminal backend

1. "Select terminal backend:" — Choose Keep current (local) (or Local if no current option is shown). This determines where Hermes executes shell commands when the agent uses its terminal tool; the local backend runs them directly on the DGX Spark, which is what this playbook assumes. The other options (Docker, Modal, SSH, Daytona, Singularity/Apptainer) run commands in containers or off-box environments and are out of scope here.

3d. Finish the wizard and verify

1. "Your minimal agent is ready. What next?" — Choose Start with everything disabled — finish now (most minimal). You can enable capabilities later at any time.

2. Reload your shell to make the hermes command available, then verify the command resolves:

   Bash

   CopiedCopy

   source ~/.bashrc
   export PATH="$HOME/.local/bin:$PATH"
   which hermes
   

3. Verify the model wiring. Run hermes to open the TUI, type hello, and press Enter; the agent should respond, confirming that the model endpoint and Hermes are wired up correctly. When you're done, type /exit to leave the chat and return to your shell. On exit, Hermes prints the exact command needed to resume this conversation later — hermes --resume <sessionId>. Save it if you want to pick up where you left off.

3e. Configure Telegram

The Blank Slate path skips messaging setup, so configure the Telegram gateway now with:

hermes gateway setup

1. "Select platforms to configure:" — The command shows a multi-select list of all supported messaging platforms (Telegram, Discord, Slack, WhatsApp, and many more). Navigate to Telegram, press SPACE to select it, then press ENTER to confirm. The remaining steps in this playbook use Telegram as the example; the same flow applies to the other supported gateways.

   TIP

   If Telegram questions are skipped: Some users see “Setup complete” or “Messaging Platforms (Gateway) configuration complete!” immediately after choosing Telegram, without token or user-ID prompts. That usually means a prior partial Telegram state exists. Re-run hermes gateway setup and select Telegram again to supply the bot token and allowed user IDs. (If the CLI suggests hermes setup gateway but that flow still skips prompts, use hermes gateway setup—that is the command most users report as working for a full Telegram reconfiguration; if it keeps skipping, see Start over from scratch in the Troubleshooting tab.) Follow the printed sudo lines to register the gateway service (if a printed sudo hermes … command fails with command not found, see the Troubleshooting tab).

2. "Telegram bot token:" — Open Telegram and start a chat with @BotFather, follow its guided flow to create a new bot, then paste the token BotFather returns into this prompt. Tip: Installing Telegram Desktop on the same machine as your SSH session lets you copy the token from Telegram and paste into the terminal without retyping it from your phone. The terminal will not echo any characters as the token is pasted — this is expected. Press Enter to submit; the installer should respond with Telegram token saved.

3. "Allowed user IDs (comma-separated, leave empty for open access):" — To restrict the bot to specific Telegram accounts, follow the on-screen instructions to look up your numeric Telegram user ID, then enter one or more IDs separated by commas. Leaving this field blank allows anyone who can reach the bot to use it, which is generally not recommended.

4. "Use your user ID (<your-id>) as the home channel? [Y/n]:" — Press Enter to accept. This designates your own Telegram account as the default channel Hermes will use for proactive messages and scheduled deliveries.

5. "Install the gateway as a systemd service? (runs in background, starts on boot) [Y/n]:" — Press Enter to accept. The gateway will run as a background service.

6. "Choose how the gateway should run in the background:" — Choose System service if you want Hermes to start at boot without requiring an interactive login. The service will still run under your user account so it can read your Hermes configuration; only installation requires sudo. If this prompt doesn't appear or you need to (re)install the service manually, run sudo "$(which hermes)" gateway install --system --run-as-user "$USER".

7. Verify the gateway. After configuration, confirm the gateway unit is active and recent logs look healthy (replace <hermes-gateway-unit> with the exact *.service name the installer printed—often something containing hermes and gateway):

   Bash

   CopiedCopy

   systemctl list-units --type=service --all | grep -i hermes
   systemctl --user list-units --type=service --all | grep -i hermes
   sudo systemctl status <hermes-gateway-unit>
   sudo journalctl -u <hermes-gateway-unit> -e --no-pager -n 50
   

   If systemctl status or systemctl --user status shows active (running) and logs are not repeating connection errors to Telegram, the service side is in good shape. If logs show TLS timeouts or “connection refused” to Telegram hosts, re-run the outbound HTTPS check at the top of this page.

8. Talk to Hermes from Telegram. The gateway is now running as a background service, so you can reach Hermes from any Telegram client without a terminal session:

   • Open Telegram (mobile or desktop) and search for your bot by the username you assigned through @BotFather.
   • Open the chat with the bot and tap Start (or send /start) on first contact.
   • Send the message hello. Hermes will reply through the bot, confirming the gateway is wired to your DGX Spark and the underlying model.

   NOTE

   After /start, Telegram may show a generic “Unknown command”-style message from the bot. That can be normal for bots that only implement free-form chat. Ignore that message and send hello anyway—Hermes should respond to normal text once the gateway and model are healthy.

   From here you can send any prompt you would normally type in the TUI — Hermes will run on your DGX Spark and stream the response back to Telegram.

Switch to a different model

You configured an initial model during the Hermes install. To switch to a different one later, restart vLLM serving the new model handle, then re-point Hermes at the same local endpoint.

1. Stop the current vLLM container (Ctrl+C in its terminal) and relaunch it with the new model handle in place of nvidia/Qwen3.6-35B-A3B-NVFP4. Use the same docker run invocation from the vLLM playbook's Run Agent Ready Qwen3.6 35B Model with vLLM tab, swapping the model handle (and any flags appropriate for the new model).

2. Launch the Hermes model picker:

   Bash

   CopiedCopy

   hermes model
   

3. At the "Select Provider" prompt, choose Custom endpoint (enter URL manually).

4. If you see the “API base URL” prompt, enter the same local vLLM endpoint as before:

   Bash

   CopiedCopy

   http://localhost:8000/v1
   

5. When Hermes lists the models served by the endpoint, choose the one you just started serving. Hermes will use it for subsequent sessions.

If you are in a non-interactive SSH session, switch models with config commands instead:

hermes config set model.provider custom
hermes config set model.base_url http://localhost:8000/v1
hermes config set model.default <new-model-handle>
hermes -z "Reply exactly MODEL_OK"

Configure tools

The Blank Slate install from Step 3 starts with the agent's tools disabled. To enable more tools or modify the existing tool configuration, run:

hermes tools

This opens the same multi-select tool list as the setup wizard (web search, browser automation, terminal, file operations, code execution, and more). Toggle entries with SPACE and press ENTER to confirm.

Resume a previous Hermes session

To pick up a past conversation, launch Hermes with the --resume flag and the session ID printed when you exited that chat:

hermes --resume <sessionId>

The TUI will reopen with the prior conversation history restored, ready for follow-up prompts.

Update Hermes

To upgrade an existing Hermes installation to the latest release, run:

hermes update

The command pulls the latest Hermes version, applies any required dependency changes, and restarts the gateway service so the new version takes effect.

Cleanup

Run cleanup from an interactive terminal. The uninstaller may refuse non-interactive subprocesses and still asks you to choose whether to keep data or perform a full uninstall. For a full wipe, choose Full uninstall and type yes at the confirmation prompt.

Because the gateway was installed as a System service in Step 3e, run the uninstall with sudo so it has permission to remove the system-scope systemd unit. If sudo hermes uninstall fails with command not found, it is because sudo does not inherit your user PATH; invoke the binary by its full path instead:

export PATH="$HOME/.local/bin:$PATH"
HERMES_BIN="$(command -v hermes || printf '%s\n' "$HOME/.local/bin/hermes")"
sudo "$HERMES_BIN" uninstall

Follow the on-screen prompts to confirm removal. The uninstaller typically:

• Stops and removes the systemd gateway service.
• Removes the hermes wrapper script and the PATH entries added to your shell profile.
• Deletes the Hermes application directory.

Data directory: The ~/.hermes directory (configuration, sessions, skills) is not always removed by uninstall, depending on the options you choose at prompts. After uninstall, check whether it still exists:

ls -la ~/.hermes

If you intend a full removal, delete it manually (this is irreversible):

rm -rf ~/.hermes

Next steps

1. Inspect the agent's reasoning. Inside the TUI, run /reasoning show to surface the model's intermediate reasoning alongside its responses. This is especially useful for following the agent's progress on multi-step or complex problems and for debugging unexpected answers.
2. Try a multi-step task to trigger skill creation. For example, ask the agent how to set up email — Hermes will walk through the configuration with you and, on completing a non-trivial task like this, may autonomously persist a reusable skill so the next email-related request is faster.
3. Configure scheduled automations via the built-in cron. For example, ask Hermes to check the price of a product online once a day and notify you on Telegram when it drops below a threshold. Hermes will schedule the task with its built-in cron and deliver each result through the messaging gateway you set up.