Libretto is an open-source CLI that lets agents turn website workflows into fast, reusable scripts you can deploy! Check it out here: https://libretto.sh/ -- I think this would be very useful for anyone (like me) who is exploring new ways in getting more control over browser automation with AI!

er, seems like Claude got a new habit recently...

Thanks to a great idea from Ray Deck, I have reduced the number of tools in the snappy.ai Xano MCP from ~180 tools and ~150,000 tokens to ~1000 tokens and 3 core tools: 1. Gemini Flash Powered Search - "What tools do I have?" (Semantic search across all tools - e.g., "create table", "list functions") 2. Info - "Tell me more about that specific tool" (returns parameters, examples, docs) 3. Execute - "Do it" (runs the tool with the right parameters) Now the initial handshake costs only ~1000 tokens instead of 150,000. Claude discovers tools as needed rather than loading everything upfront. This pattern should work for any MCP with dozens or hundreds of tools. Instead of exposing everything at once, create a search/discovery layer that lets Claude Code find what it needs when it needs it!

Spent about 10 minutes on requirements and planning with Claude Code, kicked off the plan, took a shower, and came back to this... nice. (Snappy-Xano or V2 used on this one)

Building tables and drafting functions on the phone, whilst watching the kids in the pool on vacation. Te he, I'm competing with my developer (who is manually building in Xano, back in the office) to see who gets more work done this week! (image shows me building stuff with Xano MCP tools in a client db...)