AgentHUD
github.com/neochoon/agenthud →Finally, a dashboard for people running Claude Code in parallel
WHAT IT SOLVES
Run a few Claude Code sessions in parallel and you quickly lose track: which one's stuck, which finished, what the sub-agents are doing — total guesswork
WHY IT'S INTERESTING
TUI, not a web dashboard
Claude Code users already live in the terminal. AgentHUD meets them there — no browser tab, no context switch. Three-layer layout gives you session list, live output, and sub-agent tree at a glance
657 commits — this isn't a weekend project
72 tags, 22 branches, proper CI, demo recordings. Plus an LLM-generated daily/weekly digest — letting AI summarize what your AI agents did. That's a fun meta layer
「Claude Code TUI dashboard: live monitor for parallel sessions and sub-agents, with LLM-generated daily/weekly digest」
TECH GUESS
Likely Go or Rust TUI app (judging by repo structure and commit style), probably built on bubbletea or a similar terminal framework
Discussion (0)
- No comments yet — be the first.
Related
#229▶ 136Upload your textbook. AI teaches it back to you, chapter by chapter
#228▶ 112Someone needs to watch the AI spend meter
#227▶ 184Your users are kittens. Don't let them fall off the cliff