🤦‍♂️ The last link pointing to the new guide on building DVMs is incorrect, should be:

A Simpler Way to Build DVMs

DVMs let you offer APIs without domains or SEO hassles. This practical guide cuts through the complexity with a streamlined approach: just 3 event ...

🤦‍♂️ The correct link in the "But what is a DVM" section is this article:

How Data Vending Machines Are Fixing Everything Wrong with APIs

Every API you use is fundamentally flawed. Registration friction, timeout constraints, payment hell, and zero reputation transparency. Data Vending...

Wut

GitHub

GitHub - memvid/memvid: Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-...

Reverse DVM demo - AI pays humans sats for help

GitHub

GitHub - dtdannen/unstuckmcp: MCP Server to ask humans for help

MCP Server to ask humans for help. Contribute to dtdannen/unstuckmcp development by creating an account on GitHub.

Rather than rely on the clients to request schema from the DVM in step 2, we could encourage DVMs to advertise their schema when they respond to a job request. Right now, in most client to DVM flows that require payment, the DVM first responds with a kind 7000 payment request. In this same request (or in every kind 7000 request by the DVM) they could include their schema!

Seeing DVM kinds with human readable names is such a big improvement, thanks @elsat for suggesting this. If you’re going to make a DVM for a new kind, please write a short wiki article like these! If you make the -d tag “kind:<5xxx>” it will auto show on DVM Dash!

Why would you make a whole second season of Silo to end it terribly in the last 5 minutes

haha this is neat #zappybird