ai-driven-dev/framework

Marketplace Framework AI-Driven Dev : Context Engineering, Plugins, Agents, Skills, Hooks, Templates, SDLC

What it solves

It provides a standardized, enterprise-grade Software Development Life Cycle (SDLC) for AI coding tools. It helps engineering teams unify their workflows and best practices across different tech stacks and legacy systems, reducing technical debt by turning rough ideas into reviewed and shipped pull requests through a structured process.

How it works

The framework installs a set of skills, agents, commands, and rules directly into AI coding tools (such as Claude Code, Cursor, or GitHub Copilot). It organizes the development process into a sequence of stages: framing the need, planning, implementing, validating, reviewing, and shipping. It uses a modular plugin system to handle specific parts of the SDLC, such as project memory, code transformation, and version control.

Who it’s for

Engineering teams and developers using AI coding assistants who want to move beyond ad-hoc prompts to a professional, repeatable software engineering process.

Highlights

  • IDE Agnostic: Compatible with multiple AI tools including Claude Code, Cursor, GitHub Copilot, Codex, OpenCode, and Kilo Code.
  • Modular Plugin System: Includes specialized plugins for context management (aidd-context), development (aidd-dev), version control (aidd-vcs), product management (aidd-pm), refinement (aidd-refine), and orchestration (aidd-orchestrator).
  • End-to-End Automation: Features an orchestrator that can autonomously move a feature from the framing stage to a pull request.
  • Token Optimized: Designed to be efficient with LLM token usage.

Related

  • Project
    Mathews-Tom/armory

    A collection of production-grade skills and agents for Claude Code and Claude.ai that provides battle-tested workflows for professional AI-assisted development.

  • Project
    ai-sdlc-framework/ai-sdlc

    AI‑SDLC is an open‑source decision‑engine framework that orchestrates AI‑assisted software development. It front‑loads human decisions via a Definition‑of‑Ready gate, then automatically runs a 13‑step pipeline (code generation, three independent LLM reviewers, DSSE attestation, PR creation) using an autonomous orchestrator. The system includes a terminal UI, declarative governance resources, and SDKs for TypeScript, Python, and Go. Licensed under Apache 2.0, it targets enterprises and platform teams that need reproducible, governed AI‑driven code pipelines.

  • Project
    jabrena/plinth

    An AI-native workflow and library of skills, agents, and commands designed to standardize the SDLC for modern Java Enterprise development.

  • Project
    awslabs/aidlc-workflows

    AI‑DLC is an AWS Labs framework that adds structured, auditable workflows to AI coding assistants (Claude, Kiro, Codex, Cursor, Opencode, Copilot). It provides a harness‑neutral core, multiple workflow profiles, human approval gates, and a detailed audit trail, enabling repeatable AI‑driven software delivery across many popular AI development environments.

  • Project
    Jeffallan/claude-skills

    A plugin for Claude Code providing 67 specialized developer skills and structured workflows to automate full-stack engineering tasks.