quangdang46

Looper Rust — AI skill for Claude Code

AI community

An autonomous AI development loop for Claude Code, Codex that plans, executes, and iterates on your tasks automatically — letting you complete complex workflows with a single command.

How to install Looper Rust

This entry records only its repository, not the path inside it, so there is no exact command to give. Open quangdang46/looper_rust and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Looper Rust does

An autonomous AI development loop for Claude Code, Codex that plans, executes, and iterates on your tasks automatically — letting you complete complex workflows with a single command.

Alternatives in AI

Ralph For Claude Code — by Frank Bria - An autonomous AI development framework that enables Claude Code to work iteratively on project 8k ★
Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
Paul — Plan-Apply-Unify Loop — Structured AI-assisted development for Claude Code 1.2k ★

README

looper — Autonomous AI Dev Team for Your GitHub Repos

![Release](https://img.shields.io/github/v/release/quangdang46/looper_rust?logo=github&label=release) ![CI](https://img.shields.io/github/actions/workflow/status/quangdang46/looper_rust/ci.yml?branch=main&logo=github&label=CI) ![License](https://img.shields.io/badge/License-MIT-green.svg) ![Rust](https://img.shields.io/badge/Rust-37K%20LOC-orange)

**Autonomous AI Dev Team for Your GitHub Repos.** Monitor repos, plan features, write code, review PRs, and merge — all automated via 5 agent roles. Worktree isolation, multi-vendor support, REST API + daemon.

curl -fsSL "https://github.com/quangdang46/looper_rust/releases/latest/download/install.sh" | bash

🤖 Agent Quickstart (Daemon Mode)

# Start the daemon
looper daemon start

# Add a project
looper projects add my-project --path /path/to/repo --repo-url owner/repo

# Label a GitHub issue `looper:plan` — the loop begins

**Daemon mode:** runs in background, polls GitHub for `looper:plan` issues, orchestrates Plan → Review → Work → Fix → Merge cycle automatically.

TL;DR

**The Problem** — Feature implementation is a multi-turn loop: plan → review → work → fix → merge. Each turn requires context-switching, code writing, PR pushing, and CI babysitting. Human developers burn mental bandwidth on the loop instead of the architecture.

**The Solution** — `looper` monitors GitHub repositories, and when an issue is labeled `looper:plan`, it coordinates a team of AI agents to implement the feature end-to-end: planning, reviewing, fixing, and iterating until every check passes. Unlike CI/CD pipelines that only veto broken code, looper *writes* and *fixes* code.

**Why `looper` over manual feature implementation?**

| Dimension | Looper | M