Toolkit pick · harness

Agent Looper

Quick answer: Goal-driven fix-until-green loops with a shell verifier — Cursor, Cline, OpenCode, Pi, or Codex as the worker.

Best for

Goal-driven fix-until-green loops with a shell verifier — Cursor, Cline, OpenCode, Pi, or Codex as the worker.

Skip if

You want Cursor /loop or Automations (scheduled same-chat wakes), or you only need a one-shot agent turn.

Who it fits

  • Goal-driven fix-until-green loops with a shell verifier — Cursor, Cline, OpenCode, Pi, or Codex as the worker.
  • Terminal-first engineers who live in the shell and git

Pros

Heard about agent loops? Fix-until-green: fresh worker each iteration, shell verifier decides done, optional judge. Not Cursor /loop (that is a timer in the same chat).

Cons

Editorial Toolkit pick — not an Agents-shelf coding agent or Inference-shelf provider. See Find more for broader discovery.

Facts

Locality:
Cloud-native
Surfaces:
CLI
Maturity:
General availability
Open source:
Source available

Agent standards & memory

AGENTS.md: N/ASKILL.md: N/ARules / memory: GOAL.md + loop.json + log.ndjson; optional reviewGate judge.MIT — pnpm add -D @dancingteeth/agent-looper @cursor/sdk

Compare one neighbor first

Vendor pages sell hard. Read one alternative on this site, then leave for the official link if the fit still holds.

Alternatives

Someone asks you about vibe-coding software? Share this site with them — we are adding more useful data regularly. agents.dancingteeth.net

← Back to full tool directory