> AI coding agent CLI
that verifies its work._
A terminal AI coding agent for local BYOK workflows. Resume unfinished Codex, Claude Code, Cursor, Kimi Code, or Grok work, then use /loop to write, run project checks, review, and fix until verified.
$curl -fsSL https://wukong.today/install.sh | shDefine. Loop. Verify.
Keep provider setup available during catalog outages, clarify CLI controls, and iterate until verified.
> RESUME_THE_TASK
Continue unfinished Codex, Claude Code, Cursor, Kimi Code, or Grok work without rebuilding the context.
> LOOP_UNTIL_READY
Wukong writes, checks, reviews, and fixes against one goal. If progress stalls, it stops with a clear reason.
> KNOW_WHEN_IT_IS_DONE
See whether the Loop is running, needs work, passed, or stopped—and why.
Build a verified coding-agent workflow
Concrete commands, safety boundaries, and evidence—not generic AI coding advice.
Run an AI coding agent until tests pass
Use a bounded write, check, review, and fix Loop with a trustworthy terminal result.
Use your own model API key
Understand local orchestration, provider billing, privacy boundaries, and Loop limits.
Resume work from five supported coding agents
Import read-only context, re-check the workspace, and continue or start a verified Loop.
▄▄█████▄▄
▄█████████████▄
▄▄█████████████████▄▄
▄███████████████████████▄
▀███████████████████████▀
▀▀█████████████████▀▀
▀███████████▀
▄▀▀▄ ▄███████████▄ ▄█▀
█ ▄██▀███████▀██▄██
▀▄▄▄▀██ ▀█▀█▀ ████▀
▀▀▀ ▀▀▀ ██