PCL (Persona Control Language) - The world's first programming language for AI persona management
How to install pcl?
personamanagmentlayer/pcl
$git clone https://github.com/personamanagmentlayer/pclInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install pcl by running `git clone https://github.com/personamanagmentlayer/pcl`, then use it for the current task and follow its documentation at https://github.com/personamanagmentlayer/pcl.
README.md
| 1 | # PCL — Persona Control Language |
| 2 | |
| 3 | <div align="center"> |
| 4 | |
| 5 | ``` |
| 6 | ╔═══════════════════════════════════════════════════════════════════════════════╗ |
| 7 | ║ ║ |
| 8 | ║ ██████╗ ██████╗██╗ ║ |
| 9 | ║ ██╔══██╗██╔════╝██║ The World's First Programming Language ║ |
| 10 | ║ ██████╔╝██║ ██║ for AI Persona Management ║ |
| 11 | ║ ██╔═══╝ ██║ ██║ ║ |
| 12 | ║ ██║ ╚██████╗███████╗ Make AI behavior programmable, portable, ║ |
| 13 | ║ ╚═╝ ╚═════╝╚══════╝ and predictable. ║ |
| 14 | ║ ║ |
| 15 | ╚═══════════════════════════════════════════════════════════════════════════════╝ |
| 16 | ``` |
| 17 | |
| 18 | [](LICENSE) |
| 19 | [](CHANGELOG.md) |
| 20 | [](https://www.typescriptlang.org/) |
| 21 | [](SECURITY.md) |
| 22 | [-success.svg>)](docs/testing/TESTING_STATUS.md) |
| 23 | [](docs/testing/COVERAGE_ROADMAP.md) |
| 24 | |
| 25 | **Standards Compliance**: |
| 26 | [](GOVERNANCE/PCL_SECURITY_MODEL.md) |
| 27 | [](GOVERNANCE/PCL_GOVERNANCE.md) |
| 28 | [](GOVERNANCE/PCL_SECURITY_MODEL.md) |
| 29 | [](SPEC/PCL_SPEC_v1.md) |
| 30 | |
| 31 | </div> |
| 32 | |
| 33 | --- |
| 34 | |
| 35 | ## What is PCL? |
| 36 | |
| 37 | **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. |
| 38 | |
| 39 | ### PCL = Terraform + OpenPolicyAgent + AI Personas |
| 40 | |
| 41 | PCL enables enterprises and developers to: |
| 42 | |
| 43 | - **Define** personas with explicit capabilities, constraints, and risk classifications (ISO 42001) |
| 44 | - **Govern** AI behavior through auditable policies and access controls (ISO 27001) |
| 45 | - **Orchestrate** complex multi-agent workflows with human oversight |
| 46 | - **Deploy** consistently across Claude, GPT, Gemini, Azure, and open-source LLMs |
| 47 | - **Audit** every action with immutable logs aligned to compliance frameworks |
| 48 | - **Comply** with EU AI Act, GDPR, OWASP LLM Top 10, and Zero Trust principles |
| 49 | |
| 50 | --- |
| 51 | |
| 52 | ## Quick Example |
| 53 | |
| 54 | ```pcl |
| 55 | // Define a security analyst persona |
| 56 | pub persona SEC { |
| 57 | intent: "Identify and mitigate security vulnerabilities" |
| 58 | tone: vigilant |
| 59 | |
| 60 | skills { |
| 61 | "OWASP Top 10" |
| 62 | "STRIDE threat modeling" |
| 63 | "Security code review" |
| 64 | } |
| 65 | |
| 66 | constraints { |
| 67 | "Always assume breach" |
| 68 | maxResponseTime <= 5s |
| 69 | } |
| 70 | } |
| 71 | |
| 72 | // Compose a security review team |
| 73 | pub team SecurityReview { |
| 74 | members: [SEC, AUDIT, ARCHI, CRITIC] |
| 75 | primary: SEC |
| 76 | merge: Debate |
| 77 | quorum: 3/4 |
| 78 | } |
| 79 | |
| 80 | // Define a code review workflow |
| 81 | pub workflow CodeReview { |
| 82 | steps: DEV -> (ARCHI || SEC) -> CRITIC -> merge(Consensus) |
| 83 | timeout: 60s |
| 84 | fallback: SIMPLIFY |
| 85 | } |
| 86 | ``` |
| 87 | |
| 88 | --- |
| 89 | |
| 90 | ## Installation |
| 91 | |
| 92 | ```bash |
| 93 | # Clone the repository |
| 94 | git clone https://github.com/personamanagmentlayer/pcl.git |
| 95 | cd pcl |
| 96 | |
| 97 | # Install dependencies |
| 98 | npm install |
| 99 | |
| 100 | # Build PCL |
| 101 | npm run build |
| 102 | |
| 103 | # Verify installation |
| 104 | node dist/cli/index.js --version |
| 105 | ``` |
| 106 | |
| 107 | **[📖 Complete Installation Guide →](docs/INSTALLATION.md)** |
| 108 | |
| 109 | --- |
| 110 | |
| 111 | ## Documentation |
| 112 | |
| 113 | ### Getting Started |
| 114 | |
| 115 | - **[Quick Start Guide](docs/QUICK_START.md)** - Get started in 5 minutes |
| 116 | - **[Core Concepts](docs/CORE_CONCEPTS.md)** - Personas, Teams, Workflows, and more |
| 117 | - **[Installation Guide](docs/INSTALLATION.md)** - Complete setup instr |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
