--- title: "Chat agent that reports what is trending on YouTube" kind: "Kit" category: "Research" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/1ca94f70-38dd-47df-a2b1-c15f7f77ff9f" updated: "2026-11-12" --- # Chat agent that reports what is trending on YouTube > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n chat where you name a niche. An agent searches YouTube for videos from the last two days, looks each one up for views, likes and tags, and reports what the new videos have in common. Chat agent that reports what is trending on YouTube is an n8n workflow in the Research category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow is a chat that reports what is trending on YouTube in a niche. You name a niche, and an OpenAI agent calls a search tool up to three times with different terms. The tool searches for videos from the last two days, looks each one up for its numbers and tags, and drops anything that runs three and a half minutes or less. The agent then describes what the new videos have in common. The file holds sixteen nodes, two of them sticky notes. Mindket added one so the tool has a start. ### Who it suits Creators, channel managers and content marketers who want a quick read on their niche before they plan a video. Skip it if you want a ranked list of single videos. The agent is told to describe the whole picture and not to review any one video. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Video creators | Solo YouTubers | Ask about their niche before they pick the next topic | A woodworking channel asks about small workshop builds and sees a wave of new jig videos. | | Social media agencies | Content strategists | Check a client’s niche before the weekly planning call | An agency asks about vegan meal prep and brings the report to the call. | | Online education | Course makers | Look at what learners watch on a skill before they record a lesson | A Python teacher asks about beginner projects and sees which ones draw comments. | | Brands | Marketing leads | Scan a topic in the days before a launch | A coffee gear brand asks about pour-over coffee a week before a new kettle ships. | You need a little n8n and a Google Cloud project: import a file, make two credentials, add one key and save the workflow once. ### Where to use it Any n8n that can reach OpenAI and Google’s YouTube API will run it. The video lookup reads its key from an environment variable, which n8n’s docs describe for self-hosted n8n. - n8n Cloud: import the file, and type the video lookup’s key into the node in place of the variable - Your own n8n server: set \`GOOGLE\_API\_KEY\` for n8n and leave the node as it is - n8n’s chat: the canvas chat while you test. The public chat page stays off until you turn it on in the trigger ### How to set it up Download saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. Save the workflow once after you import it, because the tool has to point at it. What you need first | Need | Detail | | --- | --- | | n8n | On n8n Cloud or on a server of your own | | OpenAI | An API key for the agent’s model | | Google Cloud | The YouTube Data API on, an OAuth2 credential for the search and an API key for the video lookup | 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. Save it, so the workflow has an ID of its own. 3. In `youtube_search`, pick this same workflow from the list. The tool runs the lower half of this file. 4. Add an OpenAI credential and select it in `openai_llm`. 5. Add a YouTube OAuth2 credential and select it in `get_videos1`. 6. Give `find_video_data1` your YouTube Data API key: set `GOOGLE_API_KEY` for n8n, or type the key into the node and remove it before you share the file. 7. Save, open the chat on the canvas and name a niche. ### How to use it Type a niche, such as home espresso or budget travel. If you give none, the agent asks and offers a few to pick from. It then searches up to three times and answers in one report. The report gives view, like and comment counts, with links to the videos and their channels. What to change for a different result | To change | Where | | --- | --- | | The report’s voice and rules | The system message of \`AI Agent\` | | The time window, region and number of results | \`get\_videos1\`: \`publishedAfter\`, \`regionCode\` and \`limit\` | | The shortest video that counts | The 210 seconds inside \`if\_longer\_than\_3\_\` | | How much the chat remembers | Context Window Length in \`window\_buffer\_memory\`, 5 by default | | The model | \`openai\_llm\` | ### Example You type this in the chat. ```text home espresso ``` The agent searches with terms of its own, such as espresso machine under a budget, then describes the pattern in the new videos. It names the views, likes and comments behind it and links the videos and channels it used. ### For newcomers and experts **If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. This file holds two workflows in one. The chat and the agent sit on the top line. The search the tool runs sits on the bottom line, and it starts at the node Mindket added. Test with one niche, then open the tool’s run under Executions to see what YouTube returned. **For experts.** The tool passes one field, `search_term`, which reaches the lower half as `query.search_term`. Where to look closer | Node | What it does | What to know | | --- | --- | --- | | \`youtube\_search\` | Tool Workflow 1.2 with one input field | It runs this same workflow, so pick it from the list after you save | | \`get\_videos1\` | YouTube search for the term, region US, last two days, 3 results, by relevance | It needs a YouTube OAuth2 credential | | \`find\_video\_data1\` | GET on the \`videos\` endpoint for each result | The key comes from \`GOOGLE\_API\_KEY\` | | \`save\_data\_to\_memory1\` | Strips links and emoji, then adds the video to one saved text | It never clears that text | ### Good to know A video with no tags stops the run, and the saved text is never cleared. - Models: \`openai\_llm\` names no model, so n8n’s default applies, \`gpt-5-mini\` (read on 12 November 2026). OpenAI’s deprecations page lists it for shutdown on 11 December 2026, with \`gpt-5.6-terra\` as the replacement - Saved text: n8n keeps a workflow’s saved data between runs only when it is published. There a later search can return videos from an earlier one. While you test by hand, nothing stays - No tags: \`group\_data1\` joins each video’s tags, so a video with none stops the run at that node - Short videos: anything of 3 minutes 30 seconds or less is left out - Quota: each tool call spends YouTube quota on one search and one lookup for each of up to three videos - Billing: OpenAI bills the agent’s calls, and one niche can take up to three tool calls - Your data: your messages and the video data go to OpenAI, and the searches go to Google - Credentials: the JSON holds none. The tool points at no workflow until you pick this one ## README ```markdown # Chat agent that reports what is trending on YouTube An n8n chat for people who make videos. You name a niche, and an AI agent searches YouTube for videos from the last two days, looks each one up for its numbers, and tells you what the new videos have in common. A search tool does the lookup, and the tool is the lower half of the same workflow. ## What is inside - `workflow.json`: the workflow as n8n exports it, sixteen nodes. Two are sticky notes, and one was added by Mindket. It holds no credential. - `README.md`: these notes. ## What we changed from the original copy - The lower half of the file had no start, because it was meant to live in a workflow of its own. Mindket added a `When Executed by Another Workflow` node in front of `get_videos1`, set to accept all data, so the tool can call this same workflow. The note on that half was reworded to say so. - `youtube_search` pointed at a workflow in its author's n8n. It now points at none until you pick this one. - `get_videos1` was linked to a YouTube credential in its author's n8n. The link is gone, so select your own. - Nothing else. Its Code nodes and expressions needed no repair. ## Before you start - An n8n instance, on n8n Cloud or your own server. - An OpenAI API key. - A Google Cloud project with the YouTube Data API on. It gives you the OAuth2 credential for `get_videos1` and the API key for `find_video_data1`. ## Set it up 1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 2. Save it, so the workflow has an ID of its own. 3. In `youtube_search`, pick this same workflow from the list. The tool runs the lower half of the file, from `When Executed by Another Workflow`. 4. Add an OpenAI credential and select it in `openai_llm`. 5. Add a YouTube OAuth2 credential and select it in `get_videos1`. 6. Give `find_video_data1` your YouTube Data API key. On a server of your own, set the environment variable `GOOGLE_API_KEY` for n8n. Where you cannot set one, replace `{{ $env["GOOGLE_API_KEY"] }}` in the `key` parameter with the key itself, and take it out again before you share the file. 7. Save, open the chat on the canvas and name a niche. ## How a request runs 1. `chat_message_received` passes your message to `AI Agent`. `window_buffer_memory` keeps the last five exchanges. 2. The agent checks that you gave a niche. If you did not, it asks and offers a few to pick from. 3. It calls `youtube_search` up to three times, each time with a different search term. The tool receives one field, `search_term`, which arrives in the lower half as `query.search_term`. 4. `get_videos1` searches YouTube for that term: region US, videos from the last two days, three results, ordered by relevance, with moderate safe search. 5. `loop_over_items1` takes one result at a time. `find_video_data1` fetches its details, with the parts `contentDetails`, `snippet` and `statistics`. 6. `if_longer_than_3_` passes a video on only when it runs longer than 210 seconds. `group_data1` keeps its id, views, likes, comments, description, title, channel name, tags and channel id. 7. `save_data_to_memory1` strips links and emoji, and adds the video to one text, with a marker between videos. 8. When the loop ends, `retrieve_data_from_memory1` and `response1` hand that text back to the agent, which writes its report. ## Change the result - The report: the system message of `AI Agent`. As written, it asks for the overall picture, not a review of any one video, with the numbers and links. - Which videos count: `get_videos1` holds the two-day window in `publishedAfter`, the region, the number of results (`limit`) and the order. The 210 seconds sit in `if_longer_than_3_`. - How much the chat remembers: Context Window Length in `window_buffer_memory`. - The model: `openai_llm`. ## Good to know - `openai_llm` names no model in the file, so the node uses its own default, `gpt-5-mini` (n8n's repository, read on 12 November 2026). OpenAI's deprecations page, read the same day, lists `gpt-5-mini` for shutdown on 11 December 2026, with `gpt-5.6-terra` as its replacement. Pick a model in the node before then. - `save_data_to_memory1` builds its text in the workflow's saved data and never clears it. n8n keeps that data between runs only on a published workflow, so there a later search can return videos from an earlier one. While you test by hand, nothing stays between runs. - `group_data1` joins each video's tags, so a video with no tags stops the run at that node. - A video of 3 minutes 30 seconds or less is left out, whatever its numbers. - Each tool call costs YouTube quota: one search, and one lookup for each of up to three videos. - OpenAI bills the agent's calls, and a niche can take up to three tool calls. - The chat trigger's public page is off until you turn it on in the trigger. Leave it off unless you want strangers to use your keys. - Your messages and the video data go to OpenAI. The searches go to Google. ``` ## What is in it 3 files, 21 KB, downloaded as a zip. ```text NOTICE.md 584 B README.md 5 KB workflow.json 15 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 11 steps, starting when another workflow calls it or on a chat message - AI: 1 step calls an AI model: AI Agent - Sign-ins: Signs in to: YouTube and OpenAI - API keys: No API key is left in the file - Step types: Mindket’s checker reads all 9 of its step types ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/1ca94f70-38dd-47df-a2b1-c15f7f77ff9f) - [Its page on Mindket](https://mindket.com/p/1ca94f70-38dd-47df-a2b1-c15f7f77ff9f)