architect-to-product
Active·★ 11·MIT·Updated 2026-09-01
A2P is an AI engineering framework delivered as an MCP server, designed to turn AI-generated code into production-ready software by enforcing engineering discipline. It introduces evidence-gated development, architecture-driven planning, and comprehensive security reviews to ensure robust and verifiable software delivery.
#AI Engineering#Software Development#Code Verification#Workflow Automation#Developer Tooling#System Engineering#Security Audit#Deployment Automation
01
Features
01Evidence-gated development: Slice progression is enforced through test and workflow evidence.
02Architecture-driven planning: Work is broken into ordered vertical slices instead of ad-hoc task generation.
03Security review built into the workflow: Includes SAST, whitebox review, and optional runtime adversarial testing.
04Deployment generation: Produces stack-specific Dockerfile, docker-compose, Caddyfile, backup/restore/verify scripts, and hardening guides.
05Code intelligence: `codebase-memory-mcp` builds a code graph instead of scanning files raw.
02
Compatibility
MCP
Protocol
Verified via docs
Claude Code
Client
Verified via docs
VS Code
Client
Verified via docs
Python
Language
Verified via docs
TypeScript
Language
Verified via docs
Docker
Deployment
Verified via docs
03
Quick start
1
$ npx architect-to-product init
04
Use cases
↳Start a new project with guardrails: Use A2P from day one to define architecture, plan slices, build with TDD, and generate deployment artifacts.
↳Harden a vibe-coded MVP: Skip straight to security, audits, refactoring, and deployment preparation for existing MVPs.
↳Re-scan before release: Transition back to security from deployment or complete; prior approvals are automatically invalidated and the full security cycle must be re-satisfied.
05
Alternatives
brigade★ 80
One local source for the MCP servers, tools, and memory your AI coding agents share, synced into each tool's native config with a review gate and a receipt for every change. No daemon, no lock-in.
oh-my-dag★ 44
The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.
oh-my-cassette★ 123
你的随身 AI 剪辑搭档 | Pocket AI co-editor for video montage — AI video editing plugin & MCP server for Claude Code, Codex, Hermes & OpenCode
SaneProcess★ 11
Workflow guardrails for coding agents and LLM-assisted development: AGENTS.md, native hooks, MCP, SaneMaster, circuit breakers, and shared process checks.
Comments
Log in to leave a comment
No comments yet. Be the first!