Notes from building ApyHub.
Engineering write-ups, product decisions, and the occasional opinion on how to ship developer infrastructure. Long enough to be useful, short enough that you'll finish it.
FILTERAGENTS
OpenClaw skills and AI agent security: why a malware scan isn't trust
341 malicious skills on ClawHub showed how agents inherit supply chain risk. What a scan catches, what it misses, and what your agent should check first.
ApyHub MCP Server: Native API Discovery and Execution for AI Agents
ApyHub shipped a native MCP server that lets AI agents search the certified API catalog at runtime and call exactly the capability they need, instead of loading hundreds of tool d…
Showing 1–2 of 2
1 / 1