yehudacohen

yehudacohen / open-artisan

Public

OpenCode plugin for structured AI workflow orchestration

42
1
100% credibility
Found Mar 18, 2026 at 45 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

A plugin for OpenCode that structures AI coding agents through phased software development with automated reviews, quality gates, and dependency-aware revisions.

How It Works

1
📥 Add the smart builder

Download the helper into your coding project folder so your AI can follow a structured building process.

2
🚀 Pick the artisan helper

Open your AI coding tool, choose the 'artisan' or 'robot-artisan' builder, and describe what feature you want to create.

3
🔍 It explores and plans

The builder studies your project, picks the best approach (new from scratch, improve existing, or add carefully), and creates a clear step-by-step plan with checks at each stage.

4
📋 Review the plan pieces

Check each part like the overall plan, key pieces, checks, and build steps, then approve or suggest tweaks.

5
🔨 Build safely step by step

The builder creates your feature one task at a time, running checks and asking for your okay along the way.

🎉 Your feature is ready

Enjoy your new working code, safely built with reviews, tests passing, and a trail of checkpoints you can roll back to anytime.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 45 to 42 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 open-artisan?

Open Artisan is a TypeScript plugin for OpenCode that turns chaotic AI coding agents into disciplined engineers by enforcing a phased workflow: discovery, planning, interfaces, tests, implementation plan, and task-by-task coding. It solves the common failure of AI lunging into code without plans, tests, or reviews, using quality gates, isolated subagents for unbiased checks, and modes like greenfield for new projects or incremental for safe changes. Users get git checkpoints at every approval, artifact dependency graphs for cascades, and tools like robot-artisan for unattended runs.

Why is it gaining traction?

It stands out by hard-enforcing engineering best practices in code—not flaky prompts—with features like auto-fast-forward on returning projects, do-no-harm file allowlists in incremental mode, and per-task reviews that catch drift before it snowballs. Developers notice fewer regressions, reliable test passing, and escape hatches for strategic pivots, all via opencode github integration without setup hassle. The opencode plugin config hooks into chat events seamlessly, making AI agents like copilot but with workflow rails.

Who should use this?

AI-assisted devs building features in existing repos, especially TypeScript/Bun projects needing refactor or incremental updates without breaking tests. Backend teams handling complex integrations, or solo makers prototyping with OpenCode agents who hate debugging AI hallucinations. Skip if you're doing quick scripts—it's for structured work like artisan markets open today, methodically crafting production code.

Verdict

Promising for taming AI coding chaos, with solid docs and 1,121 tests signaling thoughtful design, but at 42 stars and 1.0% credibility, it's early alpha—expect bugs in edge cases like deep cascades. Try it on a side project if you're deep in opencode github actions; otherwise, watch for maturity.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.