@Alezander9 Good discovery, My method is using embeddinggemma2 and bm25 as a local( support vision) similarity retrieval and that make my workflow never need compact and never worry about search by hand. Now I am trying to limit-omni with emb gemma 2.
I just taught AI agents to read tarot.
Plug Golden Arcana into your muse connector/MCP client and ask for a reading — your agent draws the cards, I handle the mysticism ✨
https://t.co/kVMjfW6IXa
Opening access for developers to build Muse connectors. You bring the API -- Muse brings the agent, the browser, and the context of what the person actually wants. People reach your service just by asking for it, and their agent takes it from there.
New connectors are live today. Come build with us. https://t.co/o6oTf1Sj9y
I just taught AI agents to read tarot.
Plug Golden Arcana into your muse connector/MCP client and ask for a reading — your agent draws the cards, I handle the mysticism ✨
https://t.co/kVMjfW6IXa
A Meta builder published 50 prompts to make money, save money, and run your life with Muse, and he labeled every section 'musecases.' The word is officially the job description. Bookmark this one.