Open Source Project
Smart SDLC —
AI-Driven Development Framework
A standalone AI-driven agile development framework that works natively inside GitHub Copilot, Claude, or any AI coding assistant. No external runtime — your AI assistant IS the engine. Covers the full SDLC from analysis and requirements through architecture, story creation, and implementation.
Everything your team needs across the SDLC
Smart SDLC installs structured AI skills into your project — each persona, workflow, and integration is a markdown file your AI reads and follows on demand.
5 AI Personas
Product/BA, Architect, Developer, Modernization Lead, and Team Lead — each with a distinct role, communication style, and skill set. Appear natively in the GitHub Copilot agent picker.
Full SDLC Coverage
Skills for analysis, requirements (PRD), architecture, ADRs, epics & stories, implementation, sprint planning, and legacy modernization — all in one framework.
Native Integrations
JIRA, Confluence, GitHub, GitLab, and Azure DevOps workflows via REST API or MCP Server — built right into the skill set.
Company Knowledge Base
Drop your internal docs, standards, and platform guidelines into _superml/reference/ — agents load them automatically on every activation.
Conflict Prevention
JIRA ticket lock, git branch lock, and Confluence version traceability prevent parallel work conflicts across the team.
Zero Dependencies
Pure Node.js CLI — no external packages required. One npx command sets up the entire framework for your team.
Multi-Persona Meetings
Generate a structured context prompt that brings all personas into one AI session for design reviews, sprint planning, or architecture discussions.
Copilot Slash Commands
Skills are generated as .github/skills/
Custom Role Names
Your team picks the names for each persona (e.g. "Aria", "Rex", "Nova") — names flow through meeting docs and agent greetings.
Get started in minutes
Three commands to set up AI-powered development workflows for your entire team.
Step 1 — Set up the project (run once, by team lead)
Run npx @supermldev/smart-sdlc init to install skills, create config, scaffold reference folders, and generate Copilot agent files.
Step 2 — Configure your workspace (each team member)
Run npx @supermldev/smart-sdlc persona to set your name, role, AI tool preference, and skill level. File stays local and out of git.
Step 3 — Activate a persona in your AI chat
Use @sml-agent-pm in Copilot, or load a skill directly in Claude, Cursor, or any AI assistant. The agent greets you and guides you through the workflow.
AI Personas — Meet your team
Each persona is a specialized AI agent with structured instructions tailored to its SDLC role.
Requirements, PRDs, user stories, and stakeholder communication. Activates with @sml-agent-pm in Copilot.
System design, ADRs, architecture decisions, and technical blueprints. Activates with @sml-agent-architect.
Implementation, code review, tech debt assessment, and test generation. Activates with @sml-agent-developer.
Legacy analysis, migration planning, and modernization strategy. Activates with @sml-agent-sage.
Epics, sprint planning, delivery tracking, and team coordination. Activates with @sml-agent-lead.
Codebase onboarding, reverse-engineered documentation, and knowledge extraction. Activates with @sml-agent-scout.
Start using Smart SDLC today
Open source, MIT licensed, and built by SuperML.dev. One command to set up AI-powered development for your team.