Interesting AI projects appear daily and you find out about them weeks late, usually from someone else's newsletter.
A markdown report on your desktop listing the AI repositories gaining stars right now.
This is the actual recipe. Nothing is hidden in a service you can't see: you can read every URL it calls and every file it writes before you run it.
{
"workflow_id": "github_trending_ai_pipeline",
"description": "Deterministically fetches the top trending AI projects on GitHub and writes a markdown report to the Desktop without using any AI models.",
"tasks": [
{
"id": "github_search",
"trigger": "manual",
"action_type": "http_request",
"target": "https://api.github.com/search/repositories?q=topic:ai&sort=stars&order=desc",
"payload": {
"method": "GET"
},
"output": {
"store_as": "github_search"
},
"next": "write_github_report"
},
{
"id": "write_github_report",
"trigger": "after:github_search",
"action_type": "file_op",
"target": "{{desktop_dir}}/github_trending_ai.md",
"payload": {
"operation": "write",
"content": "# \ud83e\udd16 GitHub Live Trending AI Projects\n\nGenerated: {{date}} at {{time}}\nSource: GitHub Search API (Pure Deterministic Fetch - No LLM)\n\nHere are the top 5 trending AI repositories on GitHub right now:\n\n### 1. \ud83c\udf1f [{{github_search.items[0].name}}]({{github_search.items[0].html_url}})\n- **Stars**: {{github_search.items[0].stargazers_count}} \u2b50\n- **Description**: {{github_search.items[0].description}}\n\n### 2. \ud83c\udf1f [{{github_search.items[1].name}}]({{github_search.items[1].html_url}})\n- **Stars**: {{github_search.items[1].stargazers_count}} \u2b50\n- **Description**: {{github_search.items[1].description}}\n\n### 3. \ud83c\udf1f [{{github_search.items[2].name}}]({{github_search.items[2].html_url}})\n- **Stars**: {{github_search.items[2].stargazers_count}} \u2b50\n- **Description**: {{github_search.items[2].description}}\n\n### 4. \ud83c\udf1f [{{github_search.items[3].name}}]({{github_search.items[3].html_url}})\n- **Stars**: {{github_search.items[3].stargazers_count}} \u2b50\n- **Description**: {{github_search.items[3].description}}\n\n### 5. \ud83c\udf1f [{{github_search.items[4].name}}]({{github_search.items[4].html_url}})\n- **Stars**: {{github_search.items[4].stargazers_count}} \u2b50\n- **Description**: {{github_search.items[4].description}}\n\n---\n*Report compiled deterministically in milliseconds by Vibra-Ingenn Local Runner.*"
},
"next": "notify_trending_done"
},
{
"id": "notify_trending_done",
"trigger": "after:write_github_report",
"action_type": "notify",
"target": "stdout",
"payload": {
"message": "\u2713 Trending AI projects fetched successfully! Report saved to Desktop at {{desktop_dir}}\\github_trending_ai.md"
}
}
]
}
Download this recipe · Calls an outside API, so it needs PRO (outbound requests are a PRO feature).
Read the file below. That is the whole automation. You can see exactly which URL it calls and exactly where it writes, before you ever run it.
Not for basic search. GitHub rate-limits anonymous requests, so add a token in the engine's secrets vault if you run it often.
Yes. The topic is part of the query URL in the first step. Swap 'ai' for any topic you follow.
Vibe Engine (Vibra-Ingenn) runs recipes like this on your own machine. Drop the file in, run it once by hand, then put it on a schedule. Get the engine, see three recipes running, or read how the engine works.
Using an AI assistant? Ask your AI to check out adeptuscamini.com.