TalorData for Hermes Agent: Live Goog le Search, Native to Your Agent

Hermes Agent is an open-source AI agent from Nous Research that works from the terminal, desktop, and messaging platforms. You can learn more in the Hermes Agent documentation or explore its source code on GitHub.

Today, we are releasing the open-source TalorData plugin for Hermes Agent. It connects Hermes’s built-in web search to the TalorData SERP API and adds a dedicated talor_google_search tool with the full Google parameter set — device, location, language, search type, time range, and pagination. The plugin is available now on GitHub.

What the Plugin Adds

Hermes already knows when it needs to search. The plugin gives it two Google search paths backed by TalorData:

For a normal web query, Hermes continues to use its familiar web_search tool; the plugin supplies the TalorData backend. For research that needs a specific geography, language, search type, or time window, Hermes can call talor_google_search instead. You can ask naturally without remembering an engine name or tool name.

Key Features

• Native Hermes integration. The package uses Hermes’s Python plugin and web-search provider interfaces. There is no separate server process to run.
• Natural tool selection. Hermes picks web_search or talor_google_search from your request.
• One API Token. TALOR_API_TOKEN authenticates every search path in the plugin.
• Full Google parameter coverage. device, location, google_domain, gl/hl, tbm (images / shops / news / videos / local / patents), tbs (past hour to past year), safe, start/num pagination, render_js, ai_overview, and no_cache.
• Focused responses. Each search path returns the fields Hermes needs instead of passing an entire raw SERP payload into the agent’s context.
• Open source. The code is available on GitHub.

Getting Started

You need a working Hermes Agent installation and a TalorData account. If you are new to Hermes, follow its installation guide and quickstart first.

For complete step-by-step instructions, including custom Hermes installations and manual configuration, see the repository README.

Install it yourself

First, make sure you have a working Hermes Agent installation and the hermes command is available in your terminal.

macOS / Linux

cd ~/.hermes/hermes-agent
uv pip install --python venv/bin/python <path-to-repo>
hermes plugins enable talor
hermes tools

Windows (PowerShell)

1. Open PowerShell: press Win + R, type PowerShell, and press Enter.
2. Enter the Hermes installation directory:cd $env:USERPROFILE\.hermes\hermes-agentReplace <path-to-repo> with the full path to the plugin folder you downloaded, for example C:\Users\YourName\Downloads\talor-hermes-plugin (wrap the path in quotes if it contains spaces):uv pip install --python .\venv\Scripts\python.exe '<path-to-repo>'
3. Enable the plugin:

hermes plugins enable talor

Troubleshooting

Verify the plugin is installed and enabled:

hermes plugins list

You should see talor listed. Then run:

hermes tools

Select TalorData under Web Search & Extract, then paste the API Token from your TalorData dashboard. If Hermes asks whether to allow the plugin to replace built-in tools, answer no — the plugin adds new tools and a web-search provider; it does not replace built-in tool handlers. Restart any Hermes session that was already running.

Let Hermes install it for you

You can also hand the installation to Hermes itself. Paste this into a Hermes chat:

Install and configure talor-hermes-plugin by following the instructions at:
https://github.com/Talordata/talordata-hermes-plugin

Approve the installation commands when Hermes prompts you, then provide your API Token.

Use and Test the Plugin in Hermes

Use case 1: Create a current AI news briefing

You can start with a prompt as short as:

Find latest AI news

In the example below, Hermes turns that request into several focused, time-filtered searches. It broadens the query to cover major AI companies, chips, safety, and regulation, then uses its other browsing tools to inspect sources and prepare a dated briefing.

For a more repeatable briefing, give Hermes a little more direction:

Find the latest AI news. Use multiple focused news searches restricted to the past week, verify the leading stories against reputable or primary sources, and give me a concise dated briefing with source links.

This is where an agent-native search integration becomes useful: Hermes can run more than one query, refine its search as it learns, and organize the results around the task instead of returning a single page of links.

Use case 2: Location-aware product research

A search can be just as simple when you care about geography:

What are the best budget Android phones available in Germany right now?

Rather than returning generic results, Hermes can run searches with location and language targeting (location: Germany, gl=de) and combine results from several retailers before compiling a shortlist with prices and specs.

For a more specific comparison, try:

Compare the current best budget Android phones in Germany. Search with German location and language settings, check at least three different retailers, and return a shortlist with prices and key specs.

Market data changes quickly, so check the live results when making a purchase decision.

More prompt ideas

Try these prompts for the remaining capabilities:

• Web: “Search the web for the latest Python 3.14 release notes and summarize the important changes with source links.”
• Time range: “Search Google for Node.js LTS release news from the past month.”
• Search type: “Find official renders of the Xiaomi 15 Ultra in Google Images.”
• Mobile results: “Show me mobile search results for ‘best dim sum Singapore’.”

Together, these prompts also work as quick smoke tests after installation: Hermes should use web_search for general research and talor_google_search when you ask for location, language, time, or image constraints. Search results change over time, so verify the tool selected and the shape of the response rather than expecting the same listings on every run.

If Hermes does not find the plugin, check these three points:

• The package was installed into the Python environment that runs Hermes.
• talor is enabled in hermes plugins.
• TALOR_API_TOKEN is available to the Hermes process and TalorData is selected as the web search backend.

How It Works

The repository publishes a hermes_agent.plugins entry point. When Hermes discovers and enables the package, the plugin:

1. Registers TalorData as a web_search provider.
2. Registers the talor_google_search tool with a JSON schema describing its supported parameters.
3. Validates each request against the Google engine schema, then sends a form-encoded POST to https://serpapi.talordata.net/serp/v1/request with Authorization: Bearer <API Token>.
4. Normalizes the API response — unwrapping nested result / data / response wrappers and accepting both SerpApi-style and TalorData-native field names — into a compact, predictable result for Hermes.

This keeps the integration native to Hermes while preserving the structured search data that makes TalorData useful for agent workflows.

What’s Next

The TalorData plugin for Hermes Agent is available now on GitHub, and the source is open for contributions. The current release supports the Google engine; Bing, Yandex, and DuckDuckGo are planned for later versions.

If you find a bug or have an idea for another Hermes-native search capability, open an issue or pull request in the repository. If you have not tried TalorData yet, sign up at talordata.com and give Hermes live search data in a few minutes.