Getting Started
Get TapPass running in under 5 minutes. No cloud account needed, everything runs locally.
What you’ll build
Section titled “What you’ll build”By the end of this guide, you’ll have:
- A running TapPass server on your machine
- An agent registered with governance flags
- Your first governed LLM call with PII detection, classification, and audit logging
| # | Page | What you’ll do |
|---|---|---|
| 1 | Installation | Install the SDK and CLI with pip install tappass |
| 2 | Quick Start | Start the server and make your first governed call |
| 3 | Your First Agent | Register an agent with governance flags and a pipeline |
| 4 | Core Concepts | Understand pipelines, capability tokens, and trust tiers |
Prerequisites
Section titled “Prerequisites”- Python 3.11+ (check with
python3 --version) - An LLM API key from OpenAI, Anthropic, or any OpenAI-compatible provider
Impatient?
Section titled “Impatient?”One command to see TapPass in action:
pip install tappass && tappass quickstartThis starts the server, registers a demo agent, and prints working Python code you can run immediately.
What’s next
Section titled “What’s next”After Getting Started, explore:
- Python SDK for the full API reference
- Providers to connect OpenAI, Anthropic, Azure, Ollama, and more
- Server for configuration, pipeline engine, and API reference
- Playbooks for client onboarding, deployment, and incident response