devforge-ai

> **Optimised SDLC AI workflow** — 10 role-specific agents × 5 phases with tracer bullet delivery and self-correction loops
=18.0.0-green?style=flat-square&logo=node.js" alt="Node.js">
An agentic SDLC orchestration system for Agentic AI. DevForge AI turns an idea into a planned, built, verified, shipped, and operated feature using role-specific agents, tracer bullet slices, quality gates, and handoff documents.
This is not a one-shot code generator. DevForge AI is a delivery workflow: product thinking first, thin vertical slices, feedback loops, security and performance checks, deployment assets, and operational follow-through.
Quickstart
1. Install the package:
2. Install the DevForge AI agents, skills, commands, and integrations into Agentic AI:
3. Restart Agentic AI, then view the interactive navigator:
4. Or run commands by scenario:
System Architecture
SDLC Phase Handoff Sequence Diagram
Ralph Loop Self-Correction Flowchart
Hyper-Scale Root Cause Analysis (1.5M Files -> 1 File)
Enterprise Multi-Tier Test Suite Matrix
Industrial Legacy Modernization (Strangler Fig)
Install From Source
Restart Agentic AI after installing. See INSTALLATION.md for update, symlink, and uninstall instructions.
Why DevForge AI Exists
DevForge AI is built around the common places AI-assisted engineering breaks down.
1. The Agent Builds The Wrong Thing
The first failure mode is misalignment. A feature request sounds obvious until the agent fills in the wrong blanks.
DevForge AI starts with /sdlc-plan, where the product-manager agent runs a structured interview, writes grill-summary.md, produces scope.json, synthesizes a PRD, and creates implementation issues. The result is a concrete build plan before any code is written.
Use this when:
- The idea is still fuzzy
- You need user stories and acceptance criteria
- You want vertical slices instead of a giant implementation blob
- You want requirements captured as artifacts, not lost in chat history
2. The Work Is Too Big To Trust
Large agent tasks fail because the feedback loop is too slow. DevForge AI breaks features into tracer bullet slices: thin increments that cut through schema, API, UI, and tests where needed.
Each slice is tracked in scope.json:
The first slice establishes the foundation. Every later slice delivers one user-visible increment and appends its result to implementation-log.md.
3. The Code Does Not Work
DevForge AI uses the Ralph Loop during build work:
- Implement one slice
- Run the relevant type checks and tests
- Retry with fresh context when verification fails
- Stop at a circuit breaker instead of looping silently
- Run cross-slice QA after feature slices are complete
This gives the agent a disciplined feedback loop instead of relying on confidence.
4. The Process Loses Context
Long SDLC sessions can drown the model in stale conversation history. DevForge AI uses handoff documents at phase gates:
Each phase reads the handoff first, then starts with bounded context. Decisions survive, but unnecessary chat history does not.
5. Shipping Is Not The End
DevForge AI includes verification, deployment, and operations phases. The workflow does not stop when code compiles.
The later phases cover:
- Security review and OWASP checks
- Performance profiling when required
- CI/CD, Docker, Kubernetes, and infrastructure artifacts
- SLOs, monitoring, runbooks, and operational readiness
- Data pipeline planning when the feature needs it
How The Pipeline Works
| Phase | Command | Primary agents | Output |
| --- | --- | --- | --- |
| Plan | /sdlc-plan | product-manager | grill-summary.md, scope.json, 01-prd.md, issues |
| Build | /sdlc-build | ux-designer, fullstack-engineer, qa-engineer | ux-design.md, code, tests, implementation-log.md |
| Verify | /sdlc-verify | security-engineer, performance-engineer | security and performance reports |