{"slug": "introducing-serpapis-hermes-agent-plugin", "title": "Introducing SerpApi’s Hermes Agent Plugin", "summary": "SerpApi released an open-source plugin for Nous Research's Hermes Agent that adds dedicated tools for local places, news, and product research via SerpApi's search engines. The plugin, available on PyPI, integrates natively with Hermes and uses a single API key for all search paths. SerpApi's plugin enables natural language tool selection for general web, Maps, News, and Shopping searches.", "body_md": "[Hermes Agent](https://hermes-agent.nousresearch.com/) is an open-source AI agent from Nous Research that can work from the terminal, desktop, and messaging platforms. You can learn more in the [Hermes Agent documentation](https://hermes-agent.nousresearch.com/docs/) or explore its source code on [GitHub](https://github.com/NousResearch/hermes-agent).\n\nToday, we are releasing the open-source [SerpApi plugin for Hermes Agent](https://github.com/serpapi/serpapi-hermes-plugin). It connects Hermes's built-in web search to SerpApi and adds dedicated tools for local places, current news, and product research. The plugin is available now on [PyPI](https://pypi.org/project/serpapi-hermes-plugin/).\n\n## What the Plugin Adds\n\nHermes already knows when it needs to search. The plugin gives it four SerpApi search paths to choose from:\n\n| What you ask for | Hermes tool | SerpApi engine |\n|---|---|---|\n| General web research | `web_search` |\n|\n\n`serpapi_maps_search`\n\n[Google Maps](https://serpapi.com/google-maps-api)`serpapi_news_search`\n\n[Google News Light](https://serpapi.com/google-news-light-api)`serpapi_shopping_search`\n\n[Google Shopping Light](https://serpapi.com/google-shopping-light-api)For a normal web query, Hermes continues to use its familiar `web_search`\n\ntool; the plugin supplies the SerpApi backend. For a local, news, or shopping request, Hermes can call the matching specialized tool. You can ask naturally without remembering an engine name or tool name.\n\nGoogle Light is the default for general web search because its compact response and low latency are a good fit for agent workflows. The specialized tools keep the useful structured fields from their respective engines, such as addresses and ratings for places, publishers and dates for news, and prices and merchants for products.\n\n## Key Features\n\n**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 chooses general web, Maps, News, or Shopping search from the user's request.**One API key.**`SERPAPI_API_KEY`\n\nauthenticates every search path in the plugin.**Focused responses.** Each search path returns the fields Hermes needs instead of passing an entire raw search response into the agent's context.**Open source and pip-installable.** The code is available on[GitHub](https://github.com/serpapi/serpapi-hermes-plugin), and the package is distributed through[PyPI](https://pypi.org/project/serpapi-hermes-plugin/).\n\n## Getting Started\n\nYou need a working Hermes Agent installation and a SerpApi account. If you are new to Hermes, follow its [installation guide](https://hermes-agent.nousresearch.com/docs/getting-started/installation) and [quickstart](https://hermes-agent.nousresearch.com/docs/getting-started/quickstart/) first.\n\nFor complete step-by-step instructions, including custom Hermes installations and manual configuration, see the [repository README](https://github.com/serpapi/serpapi-hermes-plugin#install).\n\n### Install it yourself\n\nFor a standard Hermes installation on macOS or Linux, install the package into Hermes's Python environment:\n\n```\ncd ~/.hermes/hermes-agent\nuv pip install --python venv/bin/python serpapi-hermes-plugin\nhermes plugins enable serpapi\nhermes tools\n```\n\nSelect **SerpApi** under **Web Search & Extract**, then enter the Private API Key from your [SerpApi dashboard](https://serpapi.com/dashboard). Restart any Hermes session that was already running.\n\n### Let Hermes install it for you\n\nYou can also share our installation instructions with Hermes and let the agent install, enable, configure, and verify the plugin. Paste this into a Hermes chat:\n\n```\nInstall and configure serpapi-hermes-plugin by following the instructions at:\nhttps://github.com/serpapi/serpapi-hermes-plugin#ask-hermes-to-install-it\n```\n\nApprove the installation commands when Hermes prompts you, then provide your Private API Key. The [ready-to-copy installation prompt in the README](https://github.com/serpapi/serpapi-hermes-plugin#ask-hermes-to-install-it) contains the full workflow and safety instructions.\n\n## Use and Test the Plugin in Hermes\n\n### Use case 1: Create a current AI news briefing\n\nYou can start with a prompt as short as:\n\nFind latest AI news\n\nIn the example below, Hermes turns that request into several focused news 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.\n\n*Hermes uses SerpApi for discovery, then combines the search results with its other tools to check sources and write the final briefing. The stories shown in this example reflect the time of the search and will change.*\n\nFor a more repeatable briefing, give Hermes a little more direction:\n\nFind the latest AI news. Use multiple focused news searches, verify the leading stories against reputable or primary sources, and give me a concise dated briefing with source links.\n\nThis 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.\n\n### Use case 2: Find the best cafés across Paris\n\nA local search can be just as simple:\n\nFind best Cafes in Paris\n\nRather than treating the whole city as one search, Hermes can explore different neighborhoods and intents. In this example, it searches for specialty coffee and cafés in Le Marais, Saint-Germain-des-Prés, Montmartre, Canal Saint-Martin, and the Latin Quarter before compiling a shortlist.\n\n*The resulting shortlist brings together useful Google Maps details such as ratings, review counts, addresses, price levels, and map references. Local business data can change, so check the live results when planning a visit.*\n\nFor a more specific recommendation, try:\n\nFind the best cafés in Paris. Search specialty coffee and notable neighborhoods separately, then return a varied shortlist with ratings, review counts, addresses, price levels, and Google Maps links.\n\nHermes can make several focused `serpapi_maps_search`\n\ncalls, compare the structured place results, and turn them into one useful answer.\n\n### More prompt ideas\n\nTry these prompts for the remaining search paths:\n\n**Web:**\"Search the web for the latest Python 3.14 release notes and summarize the important changes with source links.\"** News:**\"Show me the most important reusable-rocket news from the past week. Group related coverage and cite the publishers.\"** Shopping:**\"Find well-reviewed laptops under $1,200 with free shipping. Compare prices, ratings, and merchants.\"\n\nTogether, these prompts also work as quick smoke tests after installation. Hermes should use `web_search`\n\nfor general research and the dedicated Maps, News, and Shopping tools for their respective requests. 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.\n\nIf Hermes does not find the plugin, check these three points:\n\n- The package was installed into the Python environment that runs Hermes.\n`serpapi`\n\nis enabled in`hermes plugins`\n\n.`SERPAPI_API_KEY`\n\nis available to the Hermes process and SerpApi is selected as the web search backend.\n\n## How It Works\n\nThe PyPI package publishes a `hermes_agent.plugins`\n\nentry point. When Hermes discovers and enables the package, the plugin:\n\n- Registers SerpApi as a\n`web_search`\n\nprovider. - Registers separate Maps, News, and Shopping tools with schemas that describe their supported inputs.\n- Selects the corresponding SerpApi engine and validates the request.\n- Converts the API response into a compact, predictable result for Hermes.\n\nThis keeps the integration native to Hermes while preserving the structured search data that makes SerpApi useful for agent workflows.\n\n## What's Next\n\nThe SerpApi plugin for Hermes Agent is available now on [PyPI](https://pypi.org/project/serpapi-hermes-plugin/), and its source code is open on [GitHub](https://github.com/serpapi/serpapi-hermes-plugin).\n\nIf 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 SerpApi yet, [create an account](https://serpapi.com/users/sign_up) and give Hermes live search data in a few minutes.", "url": "https://wpnews.pro/news/introducing-serpapis-hermes-agent-plugin", "canonical_source": "https://serpapi.com/blog/introducing-serpapis-hermes-agent-plugin/", "published_at": "2026-07-22 13:07:10+00:00", "updated_at": "2026-07-22 13:31:48.725742+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-tools"], "entities": ["SerpApi", "Nous Research", "Hermes Agent", "Google Maps", "Google News Light", "Google Shopping Light", "PyPI", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/introducing-serpapis-hermes-agent-plugin", "markdown": "https://wpnews.pro/news/introducing-serpapis-hermes-agent-plugin.md", "text": "https://wpnews.pro/news/introducing-serpapis-hermes-agent-plugin.txt", "jsonld": "https://wpnews.pro/news/introducing-serpapis-hermes-agent-plugin.jsonld"}}