Skip to main content

ADLC Framework

Enterprise AI Agent Governance, Testing & Deployment Orchestration

Version: 3.7.1 | Constitutional Checkpoints: 58 | Components: 214


What is ADLC?

The Agent Development Lifecycle (ADLC) framework provides enterprise-grade governance for AI agent teams. It implements 7 constitutional principles with 58 checkpoints to ensure safe, reliable, and auditable AI operations.

Quick Start

# Install via npm
npx adlc@latest

# Or add as submodule to your project
git submodule add https://github.com/1xOps/adlc-framework.git .adlc
ln -s .adlc/.claude .claude
ln -s .adlc/.specify .specify

Key Features

FeatureDescription
9 Constitutional AgentsProduct Owner, Cloud Architect, QA Engineer, and 6 specialists
30 Marketplace AgentsCurated enterprise specialists across 11 domains
82 Slash CommandsCDK, Terraform, K3D, FinOps, SpecKit workflows
29 SkillsReusable capability packages with bundled references
12 Governance HooksAuto-enforced constitutional guardrails
58 CheckpointsQuality gates before deployment
3-Tier TestingSnapshot → LocalStack → AWS Sandbox
Component MarketplaceBrowse and install 400+ components

Seven Principles

  1. Acceptable Agency - HITL approval for git, deployments, cost >$100/mo
  2. Interoperability - MCP standard, OAuth, least-privilege
  3. Evaluation-First - 100% code coverage, ≥95% agent behavior
  4. Hybrid Deployment - LocalStack (Tier 2) + AWS Sandbox (Tier 3)
  5. Observability - MELT telemetry, evidence logging
  6. Governance - 58 checkpoints before deployment
  7. Agent Engineering - Orchestrator pattern (50-100 LOC agents)

Next Steps