Aditya Sharma

Automation

33 pieces Page 2 of 4 Filed under /automation

Automating the boring half of marketing and operations: crawlers, pipelines, bots and scheduled jobs, with the code and the commands to check them yourself.

  1. Connect YouTube Analytics to Google Sheets With Apps Script Google documents one clean route from YouTube Analytics into a sheet: an Apps Script service. Here is the script, the scopes, and the limits to watch. Automation 8 min
  2. AI Memory With Tagging: Tags, Embeddings and Graph Edges Are Not Interchangeable MemPalace ships five backends and the default one has a dash in the Namespaces column. Which tools expose tags, and where a tag beats a vector. AI 10 min
  3. codebase-memory-mcp vs Graphify: What Each One Actually Stores Both are alive, both refuse a vector database, and both were pushed to this week. The split is who owns the graph file. AI 10 min
  4. Choosing an AI Memory Layer: Sort Them by What Comes Back, Not by Stars A 24,587-star repo whose README says the code moved elsewhere. One axis that actually separates these tools, and the field sorted on it. AI 9 min
  5. Two Schedulers on One Site: WP-Cron Against Action Scheduler WP-Cron is one autoloaded option. Action Scheduler is three tables with nine indexes. And the batch size of 20 that lost the race was fixed in… Automation 9 min
  6. AI Memory Platform Comparison: Eleven Projects, Six Columns, Every Cell Sourced LightRAG's own README says its default storage is not for production. Storage, persistence, retrieval, licence and release date for eleven projects. AI 9 min
  7. What Self-Hosted AI Memory Actually Costs to Run Four line items, priced from published rates with the date read. Embeddings are two cents a million tokens. The bill is somewhere else. AI 10 min
  8. mem0 vs MemPalace: The Benchmark Numbers Are Not Measuring the Same Thing 94.4 and 96.6 on the same benchmark name, measuring two different quantities. What is actually comparable, and what decides it. AI 10 min
  9. MCP Server vs RAG: Which One You Actually Need They are not competing options. One is a retrieval architecture, the other is a wire protocol. The decision underneath, per data source. AI 9 min
  10. Cognee Alternatives: What You Are Actually Replacing Three reasons people leave Cognee, three different replacements, and why the most recommended swap keeps the constraint you left over. AI 10 min

One researched piece a week, on putting agents to work on real sites.

Free. One email a week. Unsubscribe in one click, and I do not send anything else.