AIObuilt

TaG

Name: TaG
Author: AIObuilt

AI community

SOURCE https://github.com/AIObuilt/TaG

Description

Trust and Governance framework for AI coding agents. Local-first guardrails for spending, credentials, deployment, and cross-project isolation.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

TaG
Trust and Governance for AI Agents

Your AI agents have no guardrails. TaG fixes that.

TaG is a **local-first trust and governance layer** that sits between your AI agents and the damage they can do. It enforces spending limits, blocks credential leaks, gates deployments on actual QA, and routes work across models based on cost — not vendor defaults.

No hosted dependency. No telemetry. No account. Clone it and it works.

If you believe AI agents need a trust layer, **[star this repo](https://github.com/AIObuilt/TaG)** — it's how open-source projects get found.

What happens without TaG

Your agent calls `stripe charges create` at 3am. Nobody stops it.

Your agent pushes to production without running tests. The deploy hook doesn't exist.

Your agent leaks your `.env` into a commit. You find out on Twitter.

Your agent burns $400 on GPT-4 when a local model could have handled it.

**TaG makes all of these impossible.**

30-Second Quick Start

git clone https://github.com/AIObuilt/TaG.git
cd TaG/tag

# See what ships out of the box
ls hooks/         # 21 governance hooks, ready to install
ls config/        # routing baseline, authority matrix, coding protocol
ls routing/       # local-first cost-aware model router

# Run the governed read-only tool loop demo
python3 tools/governed_readonly_tool_loop