
ChatGPT apps aren't websites or mobile apps. They're a new primitive - lightweight tools invoked within a conversation, surfacing minimal UI to move the user forward.


Excellent (86)
Health Score measures a project's overall trustworthiness across four key areas: contributors, development, popularity, and security.
14,669
78,935
-29% vs. Previous year
$35.2M
2,831
14,431
+16% vs. Previous year
July 11, 2019

ChatGPT apps aren't websites or mobile apps. They're a new primitive - lightweight tools invoked within a conversation, surfacing minimal UI to move the user forward.

The AI hype cycle promised full automation. Reality delivered hallucinations and agents that guess when they should ask.

The next wave of MCP servers face the same challenge: discoverability. If an LLM doesn't know when to invoke your tool, it doesn't exist.
Junghwan Park (9bow) is an AAIF Ambassador, a PyTorch Ambassador, and the lead maintainer of the PyTorch Korea User Group (PyTorchKR). A Korean version of this post is available here. TL;DR: MCP 7-28…
The Model Context Protocol (MCP) has quietly become one of the most important standards in agentic AI. In a little over a year, it went from a promising idea to the default way AI applications connec…
I wanted to know whether the whole agent loop could run locally on my M3 24GB laptop: the model, the tools, and my MCP server on the same machine, with no cloud model provider in the loop.

Weekly signal on standards, governance, and the people building the future. No fluff. Just what matters.