chaohong-ai

chaohong-ai / ai-auto-work

Public

Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development review using → test AI large language models. Capable of autonomously handling medium to large-scale engineering projects.

agent agentic-coding ai ai-coding ai-workflow
89
1
100% credibility
Found Apr 24, 2026 at 89 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Shell
AI Summary

AI Auto-Work automates complete software development workflows from user requirements to tested, committed code using collaborative AI agents.

How It Works

1
📖 Discover AI Auto-Work

You find this helpful tool in a project folder and read its simple guide to see how it turns ideas into working code.

2
💬 Describe Your Change

You type a short command like 'fix login button' telling it exactly what small fix or feature you want.

3
🧠 AI Thinks and Builds

The smart assistant reads your idea, writes the code changes, checks for mistakes, and tests everything automatically.

4
✅ Review and Fix

It double-checks its own work like a teammate would, fixing any issues until tests pass perfectly.

🎉 Your Update is Ready

Your code change is complete, tested, and safely saved—ready for you to use right away.

Sign up to see the full architecture

3 more

Sign Up Free

Star Growth

See how this repo grew from 89 to 89 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ai-auto-work?

AI Auto-Work automates the full software development cycle—from requirement research and planning to coding, testing, and git commits—using Claude for execution and Codex for adversarial reviews. Developers kick it off with simple shell commands like `/auto-work "implement user avatar upload"` or `/fast-auto-work` for quick fixes, handling medium to large projects autonomously via quality gates like compile checks and unit tests. It's a shell-based ai auto workflow that delivers production-ready code with atomic commits and self-healing knowledge bases.

Why is it gaining traction?

It stands out by enforcing mechanical gates (tests must pass before reviews) and dual-model checks that catch blind spots single LLMs miss, like concurrency bugs. No context pollution means isolated stages hand off via files only, scaling to big codebases without token limits. With 89 stars, devs dig the CLI simplicity for real-world tasks like `/research:do` tech evals or `/bug:fix` root-cause analysis.

Who should use this?

Backend engineers building Go, TypeScript, or Python services who hate manual planning loops. Solo devs or small teams tackling medium features, like auth refactors or WebSocket integrations, without full CI setups. Game devs using GDScript could adapt it for Godot projects via custom constitutions.

Verdict

Promising for ai auto works automation but low maturity—89 stars, 1.0% credibility score, and sparse tests make it experimental. Try /fast-auto-work on a side project if you're Claude/Codex power user; skip for mission-critical code until more adoption. (198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.