Pretorin Cli

🚀 Pretorin CLI

Pretorin CLI is a compliance tool for developers, which can be integrated with AI agents or your CI pipeline, providing direct access to compliance data, implementation context, and evidence workflows.

🚀 Quick Start

uv tool install pretorin
pretorin login

Run the walkthrough:

bash scripts/demo-walkthrough.sh

✨ Features

Two Usage Modes

1. Pretorin-hosted model mode: Run pretorin agent run and route model calls through Pretorin /v1 endpoints.
2. Bring-your-own-agent mode: Run pretorin mcp-serve and connect the MCP server to your existing AI tool (Claude Code, Codex CLI, Cursor, etc.).

Hosted Model Workflow (Recommended)

Use this flow when you want pretorin agent run to go through Pretorin-hosted model endpoints.

1. Authenticate with your Pretorin API key:

pretorin login

2. Optional: point model traffic to a custom/self-hosted Pretorin endpoint:

pretorin config set model_api_base_url https://platform.pretorin.com/v1

3. Verify runtime setup:

pretorin agent doctor
pretorin agent install

4. Run an agent task:

pretorin agent run "Assess AC-2 implementation gaps for my system"

Key behavior:

• Preferred setup is pretorin login with no shell-level OPENAI_API_KEY override.
• Model key precedence is: OPENAI_API_KEY -> config.api_key -> config.openai_api_key.
• If OPENAI_API_KEY is set in your shell, it overrides stored login credentials.

Add to Your AI Tool

Use this flow when you already have an AI agent/tool and want Pretorin as an MCP capability provider.

1. Claude Code

claude mcp add --transport stdio pretorin -- pretorin mcp-serve

Team setup via .mcp.json:

{
  "mcpServers": {
    "pretorin": {
      "type": "stdio",
      "command": "pretorin",
      "args": ["mcp-serve"]
    }
  }
}

2. Codex CLI

Add to ~/.codex/config.toml:

[mcp_servers.pretorin]
command = "pretorin"
args = ["mcp-serve"]

For Claude Desktop, Cursor, and Windsurf setup, see docs/MCP.md.

Core Commands

Platform-backed review and update workflows are single-scope: set one active system + framework first with pretorin context set, then run evidence, note, monitoring, narrative, or MCP-assisted compliance commands inside that scope. Multi-framework work must be split into separate runs. Evidence, narratives, and notes all support a local-first workflow: create locally, list, then push to the platform.

Artifact Authoring Rules

• Narrative and evidence markdown must be human-readable for auditors: no markdown headings, use lists/tables/code blocks/links.
• Markdown image embeds are temporarily disabled until platform-side file upload support is available.

Configuration

Credentials are stored at ~/.pretorin/config.json.

📚 Documentation

Full documentation is built with mdbook. To view it locally:

# Install mdbook (if you don't have it)
cargo install mdbook

# Serve the docs and open in your browser
cd docs && mdbook serve --open

This starts a local server at http://localhost:3000 with live-reload.

To build static HTML without serving:

cd docs && mdbook build
# Output is in docs/book/

Quick links

• CLI reference
• MCP integration guide
• Bundled skill guide
• Contributing

🔧 Technical Details

Development

git clone https://github.com/pretorin-ai/pretorin-cli.git
cd pretorin-cli
uv pip install -e ".[dev]"
pytest
ruff check src/pretorin
ruff format --check src/pretorin

📄 License

MIT License. See LICENSE.

⚠️ Important Note

Beta — Pretorin is currently in closed beta. Framework/control browsing works for everyone. Platform write features (evidence, narratives, monitoring) require a beta code. Sign up for early access.