Claude Code running inside his own Muse agent's computer
27.1K views on X · added
For funsies, I got Claude Code running on my Muse agent's computer tonight. Muse gives every agent a Linux VM with 2 vCPUs, ~8GB RAM, 100GB of persistent disk plus a scheduler, hosted artifacts and their permission system. The VM has no inbound ports, so I built a tiny xterm.js emulation of a terminal and used a scheduled task as the bridge. Every 5 seconds my Muse agent wakes up, checks for a pending prompt, shells out to claude -p, and posts the result back to the browser.
For funsies, gregce10 got Claude Code running on his Muse agent's Linux VM (2 vCPUs, ~8GB RAM, 100GB disk, plus a scheduler and hosted artifacts). He built a tiny xterm.js emulation of a terminal and used a scheduled task as the bridge: every 5 seconds his Muse agent wakes up, checks for a pending prompt, shells out to claude -p, and posts the result back to the browser — storing a session_id per thread for continuity. A delightfully meta build: an agent computer that runs a second AI inside itself.
