PCL — Persona Control Language

╔═══════════════════════════════════════════════════════════════════════════════╗
║                                                                               ║
║   ██████╗  ██████╗██╗                                                         ║
║   ██╔══██╗██╔════╝██║         The World's First Programming Language          ║
║   ██████╔╝██║     ██║              for AI Persona Management                  ║
║   ██╔═══╝ ██║     ██║                                                         ║
║   ██║     ╚██████╗███████╗    Make AI behavior programmable, portable,        ║
║   ╚═╝      ╚═════╝╚══════╝           and predictable.                         ║
║                                                                               ║
╚═══════════════════════════════════════════════════════════════════════════════╝

Standards Compliance:

---

What is PCL?

PCL (Persona Control Language) is a governance-first programming language for AI persona management and multi-agent orchestration. Unlike traditional application languages, PCL is designed for accountability, security, and compliance in AI systems.

PCL = Terraform + OpenPolicyAgent + AI Personas

PCL enables enterprises and developers to:

• Define personas with explicit capabilities, constraints, and risk classifications (ISO 42001)
• Govern AI behavior through auditable policies and access controls (ISO 27001)
• Orchestrate complex multi-agent workflows with human oversight
• Deploy consistently across Claude, GPT, Gemini, Azure, and open-source LLMs
• Audit every action with immutable logs aligned to compliance frameworks
• Comply with EU AI Act, GDPR, OWASP LLM Top 10, and Zero Trust principles

---

Quick Example

// Define a security analyst persona
pub persona SEC {
  intent: "Identify and mitigate security vulnerabilities"
  tone: vigilant

  skills {
    "OWASP Top 10"
    "STRIDE threat modeling"
    "Security code review"
  }

  constraints {
    "Always assume breach"
    maxResponseTime <= 5s
  }
}

// Compose a security review team
pub team SecurityReview {
  members: [SEC, AUDIT, ARCHI, CRITIC]
  primary: SEC
  merge: Debate
  quorum: 3/4
}

// Define a code review workflow
pub workflow CodeReview {
  steps: DEV -> (ARCHI || SEC) -> CRITIC -> merge(Consensus)
  timeout: 60s
  fallback: SIMPLIFY
}

---

Installation

# Clone the repository
git clone https://github.com/personamanagmentlayer/pcl.git
cd pcl

# Install dependencies
npm install

# Build PCL
npm run build

# Verify installation
node dist/cli/index.js --version

📖 Complete Installation Guide →

---

Documentation

Getting Started

• Quick Start Guide - Get started in 5 minutes
• Core Concepts - Personas, Teams, Workflows, and more
• Installation Guide - Complete setup instructions
• Features Overview - All features and capabilities

For Developers

• Getting Started Tutorial - Practical working introduction
• VS Code Setup - IDE configuration
• Testing Guide - Test coverage and benchmarks
• API Reference - Parser, Semantic Analysis, Code Generation

Specifications & Standards

• PCL Specification v1.0 - RFC-style formal specification
• Governance Framework - ISO 38500-aligned governance
• Security Model - ISO 27001/42001 security architecture
• Standards Overview - Complete standards alignment

Complete Documentation Index

📚 Full Documentation →

---

Key Features

Production-Ready Testing ✅

• 5,720 total tests (96.3% pass rate)
• 50.66%+ code coverage (targeting 90%)
• 153 test files covering all major modules
• Comprehensive testing: LSP, Observability, MCP, Registry, Providers, CLI, Codegen, Parser, E2E

📊 Testing Status → | 🗺️ Coverage Roadmap →

Supported AI Providers (8)

Anthropic Claude • OpenAI GPT • Google Gemini • DeepSeek • Ollama • Azure OpenAI • AWS Bedrock • Mock

🤖 Provider Guide →

Core Capabilities

• ✅ Language Server Protocol (LSP) - Full IDE support with IntelliSense, diagnostics, navigation
• ✅ Skills Ecosystem - 100% compatible with agentskills.io and Claude Code
• ✅ Model Context Protocol (MCP) - Expose personas as standardized AI services
• ✅ Registry System - 4 backends (Memory, JSON, SQLite, PostgreSQL)
• ✅ Observability - Metrics, SLO tracking, tracing, telemetry, health checks
• ✅ Code Generation - Multi-target compilation (TypeScript, Python, JSON, YAML, Markdown)

🎯 Complete Features List →

---

Production Readiness

Status: 🟡 APPROACHING PRODUCTION READY

Production Readiness Score: 78/100 (+33 from January 2026)

• ✅ Safe for: Development, prototyping, proof-of-concept, internal tools, beta testing
• 🟡 Approaching: Production, customer-facing applications (after final security audit)
• ❌ Not yet ready for: High-stakes regulated systems (needs 90% coverage)

📈 Production Readiness Report →

---

Roadmap

Phase 1: Foundation ✅ COMPLETE

• ✅ Core compiler implementation
• ✅ 8 AI provider integrations
• ✅ Registry system with 4 backends
• ✅ 50%+ test coverage baseline

Phase 2: Ecosystem ✅ COMPLETE

• ✅ Language Server Protocol (LSP)
• ✅ VS Code extension
• ✅ Skills ecosystem integration
• ✅ Model Context Protocol (MCP)

Phase 3: Scale (Q2 2026)

• 🔄 Advanced merge strategies
• 🔄 Event streaming & observability
• 🔄 90% test coverage
• 🔄 Production security audit

Phase 4: Maturity (Q4 2026)

• 📅 Visual debugging tools
• 📅 Performance profiling
• 📅 Cloud deployment
• 📅 Marketplace

🗺️ Complete Roadmap →

---

Community & Support

• 📖 Documentation - Complete guides and API reference
• 🐛 GitHub Issues - Bug reports and feature requests
• 💬 Discord - Community discussion
• 🐦 Twitter - Updates and announcements

---

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

# Fork and clone the repository
git clone https://github.com/YOUR_USERNAME/pcl.git
cd pcl

# Install dependencies
npm install

# Run tests
npm test

# Build the project
npm run build

📋 Contributing Guide → | 📜 Code of Conduct →

---

License

PCL uses dual licensing to support both software development and documentation sharing:

• Code (src/, tests/, scripts/): Apache 2.0 - Permissive software license with patent grant
• Documentation (docs/, SPEC/, GOVERNANCE/): CC BY 4.0 - Creative Commons for specs and guides
• Trademarks: IbIFACE - See Trademark Policy

This dual licensing approach follows industry best practices (Rust, Kubernetes, OpenAPI) and supports PCL's mission as a governance-first standard for enterprise AI.

For contribution licensing, see NOTICE.

---

PCL — Making AI behavior programmable, portable, and predictable.

Get Started • Documentation • Community