akasecurity/ai-tc

10 stars · Last commit 2026-08-02

Guardrails for the agent harness. Regulated data stays on your machine, and every prompt and tool call is scanned before it runs.

README preview

<p align="center"><img src="assets/banner.svg" alt="AI Traffic Control (ai-tc): intercept, inspect, and govern AI prompts and responses. Open source, Claude Code plugin, local-first." width="100%"></p>

# AI Traffic Control

**AKA Security — We secure agent harnesses at the source.**

AI Traffic Control (`ai-tc`) is an open-source control plane for coding agents. It watches an agent session's traffic (prompts, tool calls, responses, file reads), scans each event against your rule packs, and decides what happens next: monitor, warn, redact, block, or a manual exception. Secrets and regulated data like PCI, PHI, and PII are caught locally: live detection and enforcement never send them to a model or a third party. The one exception is the opt-in `/aka:setup` calibration, which does send what its history scan finds to the model API to be rated.[^egress]

![Open source](https://img.shields.io/badge/Open_source-232F3E?style=flat-square)
![Local](https://img.shields.io/badge/Local-232F3E?style=flat-square)
![Claude Code + Claude Desktop](https://img.shields.io/badge/Claude_Code_+_Claude_Desktop-232F3E?style=flat-square)
[![akasecurity.io](https://img.shields.io/badge/akasecurity.io-00E0B8?style=flat-square&labelColor=232F3E)](https://akasecurity.io)

## How it works

Every event in a session runs through one control point before it takes effect:

```
prompt · tool call · response · file read   →   ai-tc policy engine   →   monitor · warn · redact · block · exception
```

View full repository on GitHub →