An open-source software engineering operating system for AI-assisted development. agentic:guild transforms eager LLM coding assistants (like Cursor and Copilot) into disciplined software engineers with strict processes, persistent memory, and engineering-grade architectural boundaries.
<picture> <source media="(prefers-color-scheme: dark)" srcset="assets/logo-white-bg.png"> <img src="assets/logo-transparent-bg.png" alt="agentic:guild" width="420"> </picture> # Engineering-Grade AI Development [](https://github.com/jdugarte/agentic-guild) [](LICENSE) > *Stop vibe coding. Start engineering.* agentic:guild is a meta-framework that turns your AI coding assistant into a **disciplined software engineer** — one that follows the strict practices, processes, and documentation standards we've always known mattered, but rarely enforced. --- ## The problem with AI-assisted development today Left to their own devices, AI coding assistants are **eager completion engines**. They will: - Jump to solutions before understanding the problem - Silently bypass architecture boundaries they don't know about - Forget everything you agreed on three conversations ago - Generate code that *looks* right but violates your own rules The result is **vibe coding** — fast, messy, inconsistent, and increasingly difficult to maintain. You get output, but not engineering. --- ## What agentic:guild does agentic:guild injects a **software engineering operating system** into your project. It gives your AI agent: - 📋 **A process to follow** — step-by-step workflows it cannot skip or shortcut - 🧠 **A memory** — a git-ignored local state it uses to resume tasks exactly where they left off - 📐 **A constitution** — architecture and spec documents it must consult and obey before touching your code - 🚦 **Hard stops** — mandatory human approval gates before any destructive or irreversible action - 🔍 **A code review standard** — not stylistic suggestions, but numbered, actionable, engineering-grade feedback The AI doesn't just help you type faster. It **becomes a team member with a job description**. --- ## The process is the product
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.